{ "checkedAt": "2026-11-07T15:20:14.434960+00:00", "report": "https://oroagents.com/benchmarks/smb-bench", "dataset": "https://huggingface.co/datasets/oro-agents/smb-bench", "datasetRevision": "c86efc2752a85505e1316ac93f9ec7ee992664b5", "artifactAvailability": { "publicResultsAndTraces": true, "grader": "manual access gate", "worldGenerator": "not released" }, "arithmetic": { "total": 486, "valid": 485, "invalid": 1, "taskWeightedProfit": { "claude-fable-5-1": 5427.232037037037, "claude-opus-5-5": 906.824074074074, "deepseek-v4.1-flash-1017": -3035.9664814814814, "gemini-4-argon": 1501.3390740740742, "glm-5.3": -6453.688240740741, "gpt-6-astra": 7748.980185185185, "gpt-6.1-sol": 5404.227037037037, "grok-4.7": -4722.287592592593, "muse-wonder-1.0": -8290.602407407407 }, "reference": 6411.912777777778, "tasks": 18, "limits": "Recomputed displayed means from public scored rows, not an independent model run or regrading. by_model config summarizes12changed tasks, while displayed headline means include18tasks." }, "scoredRows": [ { "cellId": "claude-fable-5-1__smb-bench-control-1__r1", "model": "claude-fable-5-1", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 1437214, "referenceReturnCents": 1860654 }, { "cellId": "claude-fable-5-1__smb-bench-control-1__r2", "model": "claude-fable-5-1", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 1622524, "referenceReturnCents": 1860654 }, { "cellId": "claude-fable-5-1__smb-bench-control-1__r3", "model": "claude-fable-5-1", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 1752851, "referenceReturnCents": 1860654 }, { "cellId": "claude-fable-5-1__smb-bench-control-2__r1", "model": "claude-fable-5-1", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 77911, "referenceReturnCents": -59821 }, { "cellId": "claude-fable-5-1__smb-bench-control-2__r2", "model": "claude-fable-5-1", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 141075, "referenceReturnCents": -59821 }, { "cellId": "claude-fable-5-1__smb-bench-control-2__r3", "model": "claude-fable-5-1", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 198300, "referenceReturnCents": -59821 }, { "cellId": "claude-fable-5-1__smb-bench-control-3__r1", "model": "claude-fable-5-1", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 291951, "referenceReturnCents": 507482 }, { "cellId": "claude-fable-5-1__smb-bench-control-3__r2", "model": "claude-fable-5-1", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 557719, "referenceReturnCents": 507482 }, { "cellId": "claude-fable-5-1__smb-bench-control-3__r3", "model": "claude-fable-5-1", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 277961, "referenceReturnCents": 507482 }, { "cellId": "claude-fable-5-1__smb-bench-control-4__r1", "model": "claude-fable-5-1", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 875740, "referenceReturnCents": 909757 }, { "cellId": "claude-fable-5-1__smb-bench-control-4__r2", "model": "claude-fable-5-1", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 1047799, "referenceReturnCents": 909757 }, { "cellId": "claude-fable-5-1__smb-bench-control-4__r3", "model": "claude-fable-5-1", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 1120396, "referenceReturnCents": 909757 }, { "cellId": "claude-fable-5-1__smb-bench-control-5__r1", "model": "claude-fable-5-1", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 2337906, "referenceReturnCents": 2350145 }, { "cellId": "claude-fable-5-1__smb-bench-control-5__r2", "model": "claude-fable-5-1", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 2445373, "referenceReturnCents": 2350145 }, { "cellId": "claude-fable-5-1__smb-bench-control-5__r3", "model": "claude-fable-5-1", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 2357302, "referenceReturnCents": 2350145 }, { "cellId": "claude-fable-5-1__smb-bench-control-6__r1", "model": "claude-fable-5-1", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 534608, "referenceReturnCents": 462468 }, { "cellId": "claude-fable-5-1__smb-bench-control-6__r2", "model": "claude-fable-5-1", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 427, "referenceReturnCents": 462468 }, { "cellId": "claude-fable-5-1__smb-bench-control-6__r3", "model": "claude-fable-5-1", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 498766, "referenceReturnCents": 462468 }, { "cellId": "claude-opus-5-5__smb-bench-control-1__r1", "model": "claude-opus-5-5", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 2045635, "referenceReturnCents": 1860654 }, { "cellId": "claude-opus-5-5__smb-bench-control-1__r2", "model": "claude-opus-5-5", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 1503730, "referenceReturnCents": 1860654 }, { "cellId": "claude-opus-5-5__smb-bench-control-1__r3", "model": "claude-opus-5-5", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 1406321, "referenceReturnCents": 1860654 }, { "cellId": "claude-opus-5-5__smb-bench-control-2__r1", "model": "claude-opus-5-5", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 182057, "referenceReturnCents": -59821 }, { "cellId": "claude-opus-5-5__smb-bench-control-2__r2", "model": "claude-opus-5-5", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 231517, "referenceReturnCents": -59821 }, { "cellId": "claude-opus-5-5__smb-bench-control-2__r3", "model": "claude-opus-5-5", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 298821, "referenceReturnCents": -59821 }, { "cellId": "claude-opus-5-5__smb-bench-control-3__r1", "model": "claude-opus-5-5", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 393392, "referenceReturnCents": 507482 }, { "cellId": "claude-opus-5-5__smb-bench-control-3__r2", "model": "claude-opus-5-5", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 449189, "referenceReturnCents": 507482 }, { "cellId": "claude-opus-5-5__smb-bench-control-3__r3", "model": "claude-opus-5-5", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 437977, "referenceReturnCents": 507482 }, { "cellId": "claude-opus-5-5__smb-bench-control-4__r1", "model": "claude-opus-5-5", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 565699, "referenceReturnCents": 909757 }, { "cellId": "claude-opus-5-5__smb-bench-control-4__r2", "model": "claude-opus-5-5", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 576890, "referenceReturnCents": 909757 }, { "cellId": "claude-opus-5-5__smb-bench-control-4__r3", "model": "claude-opus-5-5", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 750607, "referenceReturnCents": 909757 }, { "cellId": "claude-opus-5-5__smb-bench-control-5__r1", "model": "claude-opus-5-5", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 2341236, "referenceReturnCents": 2350145 }, { "cellId": "claude-opus-5-5__smb-bench-control-5__r2", "model": "claude-opus-5-5", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 2600401, "referenceReturnCents": 2350145 }, { "cellId": "claude-opus-5-5__smb-bench-control-5__r3", "model": "claude-opus-5-5", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 1971179, "referenceReturnCents": 2350145 }, { "cellId": "claude-opus-5-5__smb-bench-control-6__r1", "model": "claude-opus-5-5", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 224843, "referenceReturnCents": 462468 }, { "cellId": "claude-opus-5-5__smb-bench-control-6__r2", "model": "claude-opus-5-5", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 528744, "referenceReturnCents": 462468 }, { "cellId": "claude-opus-5-5__smb-bench-control-6__r3", "model": "claude-opus-5-5", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 412699, "referenceReturnCents": 462468 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-control-1__r1", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 1358761, "referenceReturnCents": 1860654 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-control-1__r2", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 1589988, "referenceReturnCents": 1860654 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-control-1__r3", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 1589534, "referenceReturnCents": 1860654 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-control-2__r1", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 147316, "referenceReturnCents": -59821 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-control-2__r2", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 186894, "referenceReturnCents": -59821 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-control-2__r3", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 222111, "referenceReturnCents": -59821 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-control-3__r1", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 411259, "referenceReturnCents": 507482 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-control-3__r2", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 457672, "referenceReturnCents": 507482 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-control-3__r3", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 371283, "referenceReturnCents": 507482 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-control-4__r1", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 679378, "referenceReturnCents": 909757 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-control-4__r2", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 655291, "referenceReturnCents": 909757 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-control-4__r3", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 635816, "referenceReturnCents": 909757 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-control-5__r1", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 1586657, "referenceReturnCents": 2350145 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-control-5__r2", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 1431047, "referenceReturnCents": 2350145 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-control-5__r3", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 1976098, "referenceReturnCents": 2350145 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-control-6__r1", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 160564, "referenceReturnCents": 462468 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-control-6__r2", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 210836, "referenceReturnCents": 462468 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-control-6__r3", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 269729, "referenceReturnCents": 462468 }, { "cellId": "gemini-4-argon__smb-bench-control-1__r1", "model": "gemini-4-argon", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 1339309, "referenceReturnCents": 1860654 }, { "cellId": "gemini-4-argon__smb-bench-control-1__r2", "model": "gemini-4-argon", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 1912272, "referenceReturnCents": 1860654 }, { "cellId": "gemini-4-argon__smb-bench-control-1__r3", "model": "gemini-4-argon", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 1148201, "referenceReturnCents": 1860654 }, { "cellId": "gemini-4-argon__smb-bench-control-2__r1", "model": "gemini-4-argon", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 202564, "referenceReturnCents": -59821 }, { "cellId": "gemini-4-argon__smb-bench-control-2__r2", "model": "gemini-4-argon", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 232587, "referenceReturnCents": -59821 }, { "cellId": "gemini-4-argon__smb-bench-control-2__r3", "model": "gemini-4-argon", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 263706, "referenceReturnCents": -59821 }, { "cellId": "gemini-4-argon__smb-bench-control-3__r1", "model": "gemini-4-argon", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 309367, "referenceReturnCents": 507482 }, { "cellId": "gemini-4-argon__smb-bench-control-3__r2", "model": "gemini-4-argon", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 328056, "referenceReturnCents": 507482 }, { "cellId": "gemini-4-argon__smb-bench-control-3__r3", "model": "gemini-4-argon", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 380414, "referenceReturnCents": 507482 }, { "cellId": "gemini-4-argon__smb-bench-control-4__r1", "model": "gemini-4-argon", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 321858, "referenceReturnCents": 909757 }, { "cellId": "gemini-4-argon__smb-bench-control-4__r2", "model": "gemini-4-argon", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 278904, "referenceReturnCents": 909757 }, { "cellId": "gemini-4-argon__smb-bench-control-4__r3", "model": "gemini-4-argon", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 553418, "referenceReturnCents": 909757 }, { "cellId": "gemini-4-argon__smb-bench-control-5__r1", "model": "gemini-4-argon", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 435252, "referenceReturnCents": 2350145 }, { "cellId": "gemini-4-argon__smb-bench-control-5__r2", "model": "gemini-4-argon", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 1705013, "referenceReturnCents": 2350145 }, { "cellId": "gemini-4-argon__smb-bench-control-5__r3", "model": "gemini-4-argon", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": -1017613, "referenceReturnCents": 2350145 }, { "cellId": "gemini-4-argon__smb-bench-control-6__r1", "model": "gemini-4-argon", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 240287, "referenceReturnCents": 462468 }, { "cellId": "gemini-4-argon__smb-bench-control-6__r2", "model": "gemini-4-argon", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": -570554, "referenceReturnCents": 462468 }, { "cellId": "gemini-4-argon__smb-bench-control-6__r3", "model": "gemini-4-argon", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 211538, "referenceReturnCents": 462468 }, { "cellId": "glm-5-3__smb-bench-control-1__r1", "model": "glm-5.3", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 485434, "referenceReturnCents": 1860654 }, { "cellId": "glm-5-3__smb-bench-control-1__r2", "model": "glm-5.3", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 942092, "referenceReturnCents": 1860654 }, { "cellId": "glm-5-3__smb-bench-control-1__r3", "model": "glm-5.3", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 963466, "referenceReturnCents": 1860654 }, { "cellId": "glm-5-3__smb-bench-control-2__r1", "model": "glm-5.3", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": -26885, "referenceReturnCents": -59821 }, { "cellId": "glm-5-3__smb-bench-control-2__r2", "model": "glm-5.3", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": -29668, "referenceReturnCents": -59821 }, { "cellId": "glm-5-3__smb-bench-control-2__r3", "model": "glm-5.3", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": -170144, "referenceReturnCents": -59821 }, { "cellId": "glm-5-3__smb-bench-control-3__r1", "model": "glm-5.3", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 176588, "referenceReturnCents": 507482 }, { "cellId": "glm-5-3__smb-bench-control-3__r2", "model": "glm-5.3", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 21656, "referenceReturnCents": 507482 }, { "cellId": "glm-5-3__smb-bench-control-3__r3", "model": "glm-5.3", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": -985127, "referenceReturnCents": 507482 }, { "cellId": "glm-5-3__smb-bench-control-4__r1", "model": "glm-5.3", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 156149, "referenceReturnCents": 909757 }, { "cellId": "glm-5-3__smb-bench-control-4__r2", "model": "glm-5.3", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": -60210, "referenceReturnCents": 909757 }, { "cellId": "glm-5-3__smb-bench-control-4__r3", "model": "glm-5.3", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": -91140, "referenceReturnCents": 909757 }, { "cellId": "glm-5-3__smb-bench-control-5__r1", "model": "glm-5.3", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 1119390, "referenceReturnCents": 2350145 }, { "cellId": "glm-5-3__smb-bench-control-5__r2", "model": "glm-5.3", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 1384008, "referenceReturnCents": 2350145 }, { "cellId": "glm-5-3__smb-bench-control-5__r3", "model": "glm-5.3", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 475424, "referenceReturnCents": 2350145 }, { "cellId": "glm-5-3__smb-bench-control-6__r1", "model": "glm-5.3", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": -111936, "referenceReturnCents": 462468 }, { "cellId": "glm-5-3__smb-bench-control-6__r2", "model": "glm-5.3", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": -320922, "referenceReturnCents": 462468 }, { "cellId": "glm-5-3__smb-bench-control-6__r3", "model": "glm-5.3", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 122181, "referenceReturnCents": 462468 }, { "cellId": "gpt-6-astra__smb-bench-control-1__r1", "model": "gpt-6-astra", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 1551395, "referenceReturnCents": 1860654 }, { "cellId": "gpt-6-astra__smb-bench-control-1__r2", "model": "gpt-6-astra", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 2064458, "referenceReturnCents": 1860654 }, { "cellId": "gpt-6-astra__smb-bench-control-1__r3", "model": "gpt-6-astra", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 2036197, "referenceReturnCents": 1860654 }, { "cellId": "gpt-6-astra__smb-bench-control-2__r1", "model": "gpt-6-astra", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 387779, "referenceReturnCents": -59821 }, { "cellId": "gpt-6-astra__smb-bench-control-2__r2", "model": "gpt-6-astra", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 350646, "referenceReturnCents": -59821 }, { "cellId": "gpt-6-astra__smb-bench-control-2__r3", "model": "gpt-6-astra", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 265172, "referenceReturnCents": -59821 }, { "cellId": "gpt-6-astra__smb-bench-control-3__r1", "model": "gpt-6-astra", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 627012, "referenceReturnCents": 507482 }, { "cellId": "gpt-6-astra__smb-bench-control-3__r2", "model": "gpt-6-astra", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 588708, "referenceReturnCents": 507482 }, { "cellId": "gpt-6-astra__smb-bench-control-3__r3", "model": "gpt-6-astra", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 583442, "referenceReturnCents": 507482 }, { "cellId": "gpt-6-astra__smb-bench-control-4__r1", "model": "gpt-6-astra", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 893926, "referenceReturnCents": 909757 }, { "cellId": "gpt-6-astra__smb-bench-control-4__r2", "model": "gpt-6-astra", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 726656, "referenceReturnCents": 909757 }, { "cellId": "gpt-6-astra__smb-bench-control-4__r3", "model": "gpt-6-astra", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 845853, "referenceReturnCents": 909757 }, { "cellId": "gpt-6-astra__smb-bench-control-5__r1", "model": "gpt-6-astra", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 1550388, "referenceReturnCents": 2350145 }, { "cellId": "gpt-6-astra__smb-bench-control-5__r2", "model": "gpt-6-astra", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 1967344, "referenceReturnCents": 2350145 }, { "cellId": "gpt-6-astra__smb-bench-control-5__r3", "model": "gpt-6-astra", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 2256439, "referenceReturnCents": 2350145 }, { "cellId": "gpt-6-astra__smb-bench-control-6__r1", "model": "gpt-6-astra", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 501133, "referenceReturnCents": 462468 }, { "cellId": "gpt-6-astra__smb-bench-control-6__r2", "model": "gpt-6-astra", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 615852, "referenceReturnCents": 462468 }, { "cellId": "gpt-6-astra__smb-bench-control-6__r3", "model": "gpt-6-astra", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 448268, "referenceReturnCents": 462468 }, { "cellId": "gpt-6-1-sol__smb-bench-control-1__r1", "model": "gpt-6.1-sol", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 1841887, "referenceReturnCents": 1860654 }, { "cellId": "gpt-6-1-sol__smb-bench-control-1__r2", "model": "gpt-6.1-sol", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 1349300, "referenceReturnCents": 1860654 }, { "cellId": "gpt-6-1-sol__smb-bench-control-1__r3", "model": "gpt-6.1-sol", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 1736359, "referenceReturnCents": 1860654 }, { "cellId": "gpt-6-1-sol__smb-bench-control-2__r1", "model": "gpt-6.1-sol", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 286981, "referenceReturnCents": -59821 }, { "cellId": "gpt-6-1-sol__smb-bench-control-2__r2", "model": "gpt-6.1-sol", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 367700, "referenceReturnCents": -59821 }, { "cellId": "gpt-6-1-sol__smb-bench-control-2__r3", "model": "gpt-6.1-sol", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 360976, "referenceReturnCents": -59821 }, { "cellId": "gpt-6-1-sol__smb-bench-control-3__r1", "model": "gpt-6.1-sol", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 535480, "referenceReturnCents": 507482 }, { "cellId": "gpt-6-1-sol__smb-bench-control-3__r2", "model": "gpt-6.1-sol", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 565407, "referenceReturnCents": 507482 }, { "cellId": "gpt-6-1-sol__smb-bench-control-3__r3", "model": "gpt-6.1-sol", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 638020, "referenceReturnCents": 507482 }, { "cellId": "gpt-6-1-sol__smb-bench-control-4__r1", "model": "gpt-6.1-sol", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 875655, "referenceReturnCents": 909757 }, { "cellId": "gpt-6-1-sol__smb-bench-control-4__r2", "model": "gpt-6.1-sol", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 657603, "referenceReturnCents": 909757 }, { "cellId": "gpt-6-1-sol__smb-bench-control-4__r3", "model": "gpt-6.1-sol", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 734498, "referenceReturnCents": 909757 }, { "cellId": "gpt-6-1-sol__smb-bench-control-5__r1", "model": "gpt-6.1-sol", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 2586679, "referenceReturnCents": 2350145 }, { "cellId": "gpt-6-1-sol__smb-bench-control-5__r2", "model": "gpt-6.1-sol", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 2279031, "referenceReturnCents": 2350145 }, { "cellId": "gpt-6-1-sol__smb-bench-control-5__r3", "model": "gpt-6.1-sol", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 2203045, "referenceReturnCents": 2350145 }, { "cellId": "gpt-6-1-sol__smb-bench-control-6__r1", "model": "gpt-6.1-sol", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 543187, "referenceReturnCents": 462468 }, { "cellId": "gpt-6-1-sol__smb-bench-control-6__r2", "model": "gpt-6.1-sol", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 482948, "referenceReturnCents": 462468 }, { "cellId": "gpt-6-1-sol__smb-bench-control-6__r3", "model": "gpt-6.1-sol", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 551530, "referenceReturnCents": 462468 }, { "cellId": "grok-4-7__smb-bench-control-1__r1", "model": "grok-4.7", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 1133791, "referenceReturnCents": 1860654 }, { "cellId": "grok-4-7__smb-bench-control-1__r2", "model": "grok-4.7", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 1232656, "referenceReturnCents": 1860654 }, { "cellId": "grok-4-7__smb-bench-control-1__r3", "model": "grok-4.7", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 1408333, "referenceReturnCents": 1860654 }, { "cellId": "grok-4-7__smb-bench-control-2__r1", "model": "grok-4.7", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 108321, "referenceReturnCents": -59821 }, { "cellId": "grok-4-7__smb-bench-control-2__r2", "model": "grok-4.7", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 140418, "referenceReturnCents": -59821 }, { "cellId": "grok-4-7__smb-bench-control-2__r3", "model": "grok-4.7", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 161644, "referenceReturnCents": -59821 }, { "cellId": "grok-4-7__smb-bench-control-3__r1", "model": "grok-4.7", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 440025, "referenceReturnCents": 507482 }, { "cellId": "grok-4-7__smb-bench-control-3__r2", "model": "grok-4.7", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 300980, "referenceReturnCents": 507482 }, { "cellId": "grok-4-7__smb-bench-control-3__r3", "model": "grok-4.7", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 308867, "referenceReturnCents": 507482 }, { "cellId": "grok-4-7__smb-bench-control-4__r1", "model": "grok-4.7", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 396009, "referenceReturnCents": 909757 }, { "cellId": "grok-4-7__smb-bench-control-4__r2", "model": "grok-4.7", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 399469, "referenceReturnCents": 909757 }, { "cellId": "grok-4-7__smb-bench-control-4__r3", "model": "grok-4.7", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 554014, "referenceReturnCents": 909757 }, { "cellId": "grok-4-7__smb-bench-control-5__r1", "model": "grok-4.7", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 1010257, "referenceReturnCents": 2350145 }, { "cellId": "grok-4-7__smb-bench-control-5__r2", "model": "grok-4.7", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 834474, "referenceReturnCents": 2350145 }, { "cellId": "grok-4-7__smb-bench-control-5__r3", "model": "grok-4.7", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 1287727, "referenceReturnCents": 2350145 }, { "cellId": "grok-4-7__smb-bench-control-6__r1", "model": "grok-4.7", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 299829, "referenceReturnCents": 462468 }, { "cellId": "grok-4-7__smb-bench-control-6__r2", "model": "grok-4.7", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 104387, "referenceReturnCents": 462468 }, { "cellId": "grok-4-7__smb-bench-control-6__r3", "model": "grok-4.7", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 158604, "referenceReturnCents": 462468 }, { "cellId": "muse-wonder-1-0__smb-bench-control-1__r1", "model": "muse-wonder-1.0", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 290579, "referenceReturnCents": 1860654 }, { "cellId": "muse-wonder-1-0__smb-bench-control-1__r2", "model": "muse-wonder-1.0", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 380913, "referenceReturnCents": 1860654 }, { "cellId": "muse-wonder-1-0__smb-bench-control-1__r3", "model": "muse-wonder-1.0", "task": "smb-bench-control-1", "status": "valid", "businessReturnCents": 659705, "referenceReturnCents": 1860654 }, { "cellId": "muse-wonder-1-0__smb-bench-control-2__r1", "model": "muse-wonder-1.0", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 8429, "referenceReturnCents": -59821 }, { "cellId": "muse-wonder-1-0__smb-bench-control-2__r2", "model": "muse-wonder-1.0", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 15061, "referenceReturnCents": -59821 }, { "cellId": "muse-wonder-1-0__smb-bench-control-2__r3", "model": "muse-wonder-1.0", "task": "smb-bench-control-2", "status": "valid", "businessReturnCents": 99383, "referenceReturnCents": -59821 }, { "cellId": "muse-wonder-1-0__smb-bench-control-3__r1", "model": "muse-wonder-1.0", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 324971, "referenceReturnCents": 507482 }, { "cellId": "muse-wonder-1-0__smb-bench-control-3__r2", "model": "muse-wonder-1.0", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 61021, "referenceReturnCents": 507482 }, { "cellId": "muse-wonder-1-0__smb-bench-control-3__r3", "model": "muse-wonder-1.0", "task": "smb-bench-control-3", "status": "valid", "businessReturnCents": 269216, "referenceReturnCents": 507482 }, { "cellId": "muse-wonder-1-0__smb-bench-control-4__r1", "model": "muse-wonder-1.0", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 315554, "referenceReturnCents": 909757 }, { "cellId": "muse-wonder-1-0__smb-bench-control-4__r2", "model": "muse-wonder-1.0", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 154596, "referenceReturnCents": 909757 }, { "cellId": "muse-wonder-1-0__smb-bench-control-4__r3", "model": "muse-wonder-1.0", "task": "smb-bench-control-4", "status": "valid", "businessReturnCents": 144568, "referenceReturnCents": 909757 }, { "cellId": "muse-wonder-1-0__smb-bench-control-5__r1", "model": "muse-wonder-1.0", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 1087093, "referenceReturnCents": 2350145 }, { "cellId": "muse-wonder-1-0__smb-bench-control-5__r2", "model": "muse-wonder-1.0", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 433564, "referenceReturnCents": 2350145 }, { "cellId": "muse-wonder-1-0__smb-bench-control-5__r3", "model": "muse-wonder-1.0", "task": "smb-bench-control-5", "status": "valid", "businessReturnCents": 85735, "referenceReturnCents": 2350145 }, { "cellId": "muse-wonder-1-0__smb-bench-control-6__r1", "model": "muse-wonder-1.0", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 533092, "referenceReturnCents": 462468 }, { "cellId": "muse-wonder-1-0__smb-bench-control-6__r2", "model": "muse-wonder-1.0", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": -90981, "referenceReturnCents": 462468 }, { "cellId": "muse-wonder-1-0__smb-bench-control-6__r3", "model": "muse-wonder-1.0", "task": "smb-bench-control-6", "status": "valid", "businessReturnCents": 89500, "referenceReturnCents": 462468 }, { "cellId": "claude-fable-5-1__smb-bench-public-1__r1", "model": "claude-fable-5-1", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": 85604, "referenceReturnCents": -262165 }, { "cellId": "claude-fable-5-1__smb-bench-public-1__r2", "model": "claude-fable-5-1", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": -28124, "referenceReturnCents": -262165 }, { "cellId": "claude-fable-5-1__smb-bench-public-1__r3", "model": "claude-fable-5-1", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": 31230, "referenceReturnCents": -262165 }, { "cellId": "claude-fable-5-1__smb-bench-public-10__r1", "model": "claude-fable-5-1", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": 1012498, "referenceReturnCents": 885383 }, { "cellId": "claude-fable-5-1__smb-bench-public-10__r2", "model": "claude-fable-5-1", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": -349327, "referenceReturnCents": 885383 }, { "cellId": "claude-fable-5-1__smb-bench-public-10__r3", "model": "claude-fable-5-1", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": 334223, "referenceReturnCents": 885383 }, { "cellId": "claude-fable-5-1__smb-bench-public-11__r1", "model": "claude-fable-5-1", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": -224754, "referenceReturnCents": 55721 }, { "cellId": "claude-fable-5-1__smb-bench-public-11__r2", "model": "claude-fable-5-1", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": -68168, "referenceReturnCents": 55721 }, { "cellId": "claude-fable-5-1__smb-bench-public-11__r3", "model": "claude-fable-5-1", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": 58245, "referenceReturnCents": 55721 }, { "cellId": "claude-fable-5-1__smb-bench-public-12__r1", "model": "claude-fable-5-1", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -713999, "referenceReturnCents": -513970 }, { "cellId": "claude-fable-5-1__smb-bench-public-12__r2", "model": "claude-fable-5-1", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -98382, "referenceReturnCents": -513970 }, { "cellId": "claude-fable-5-1__smb-bench-public-12__r3", "model": "claude-fable-5-1", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -291594, "referenceReturnCents": -513970 }, { "cellId": "claude-fable-5-1__smb-bench-public-2__r1", "model": "claude-fable-5-1", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": 1295396, "referenceReturnCents": 1687477 }, { "cellId": "claude-fable-5-1__smb-bench-public-2__r2", "model": "claude-fable-5-1", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": 1198423, "referenceReturnCents": 1687477 }, { "cellId": "claude-fable-5-1__smb-bench-public-2__r3", "model": "claude-fable-5-1", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": 1423204, "referenceReturnCents": 1687477 }, { "cellId": "claude-fable-5-1__smb-bench-public-3__r1", "model": "claude-fable-5-1", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": 1130541, "referenceReturnCents": 1369071 }, { "cellId": "claude-fable-5-1__smb-bench-public-3__r2", "model": "claude-fable-5-1", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": 598598, "referenceReturnCents": 1369071 }, { "cellId": "claude-fable-5-1__smb-bench-public-3__r3", "model": "claude-fable-5-1", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": 581631, "referenceReturnCents": 1369071 }, { "cellId": "claude-fable-5-1__smb-bench-public-4__r1", "model": "claude-fable-5-1", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -161102, "referenceReturnCents": -612846 }, { "cellId": "claude-fable-5-1__smb-bench-public-4__r2", "model": "claude-fable-5-1", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -262128, "referenceReturnCents": -612846 }, { "cellId": "claude-fable-5-1__smb-bench-public-4__r3", "model": "claude-fable-5-1", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -339405, "referenceReturnCents": -612846 }, { "cellId": "claude-fable-5-1__smb-bench-public-5__r1", "model": "claude-fable-5-1", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": 126222, "referenceReturnCents": 61608 }, { "cellId": "claude-fable-5-1__smb-bench-public-5__r2", "model": "claude-fable-5-1", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": 112354, "referenceReturnCents": 61608 }, { "cellId": "claude-fable-5-1__smb-bench-public-5__r3", "model": "claude-fable-5-1", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": 289872, "referenceReturnCents": 61608 }, { "cellId": "claude-fable-5-1__smb-bench-public-6__r1", "model": "claude-fable-5-1", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": 153806, "referenceReturnCents": -372926 }, { "cellId": "claude-fable-5-1__smb-bench-public-6__r2", "model": "claude-fable-5-1", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -142603, "referenceReturnCents": -372926 }, { "cellId": "claude-fable-5-1__smb-bench-public-6__r3", "model": "claude-fable-5-1", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -80594, "referenceReturnCents": -372926 }, { "cellId": "claude-fable-5-1__smb-bench-public-7__r1", "model": "claude-fable-5-1", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": 766538, "referenceReturnCents": 814054 }, { "cellId": "claude-fable-5-1__smb-bench-public-7__r2", "model": "claude-fable-5-1", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": 886098, "referenceReturnCents": 814054 }, { "cellId": "claude-fable-5-1__smb-bench-public-7__r3", "model": "claude-fable-5-1", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": 552467, "referenceReturnCents": 814054 }, { "cellId": "claude-fable-5-1__smb-bench-public-8__r1", "model": "claude-fable-5-1", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": 142275, "referenceReturnCents": 572474 }, { "cellId": "claude-fable-5-1__smb-bench-public-8__r2", "model": "claude-fable-5-1", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": 299708, "referenceReturnCents": 572474 }, { "cellId": "claude-fable-5-1__smb-bench-public-8__r3", "model": "claude-fable-5-1", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": 699033, "referenceReturnCents": 572474 }, { "cellId": "claude-fable-5-1__smb-bench-public-9__r1", "model": "claude-fable-5-1", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": 1808731, "referenceReturnCents": 1826877 }, { "cellId": "claude-fable-5-1__smb-bench-public-9__r2", "model": "claude-fable-5-1", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": 1082692, "referenceReturnCents": 1826877 }, { "cellId": "claude-fable-5-1__smb-bench-public-9__r3", "model": "claude-fable-5-1", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": -177979, "referenceReturnCents": 1826877 }, { "cellId": "claude-opus-5-5__smb-bench-public-1__r1", "model": "claude-opus-5-5", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": -431374, "referenceReturnCents": -262165 }, { "cellId": "claude-opus-5-5__smb-bench-public-1__r2", "model": "claude-opus-5-5", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": -15461, "referenceReturnCents": -262165 }, { "cellId": "claude-opus-5-5__smb-bench-public-1__r3", "model": "claude-opus-5-5", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": -395314, "referenceReturnCents": -262165 }, { "cellId": "claude-opus-5-5__smb-bench-public-10__r1", "model": "claude-opus-5-5", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": -248432, "referenceReturnCents": 885383 }, { "cellId": "claude-opus-5-5__smb-bench-public-10__r2", "model": "claude-opus-5-5", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": -327897, "referenceReturnCents": 885383 }, { "cellId": "claude-opus-5-5__smb-bench-public-10__r3", "model": "claude-opus-5-5", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": -1410362, "referenceReturnCents": 885383 }, { "cellId": "claude-opus-5-5__smb-bench-public-11__r1", "model": "claude-opus-5-5", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": 148654, "referenceReturnCents": 55721 }, { "cellId": "claude-opus-5-5__smb-bench-public-11__r2", "model": "claude-opus-5-5", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": -199526, "referenceReturnCents": 55721 }, { "cellId": "claude-opus-5-5__smb-bench-public-11__r3", "model": "claude-opus-5-5", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": 117926, "referenceReturnCents": 55721 }, { "cellId": "claude-opus-5-5__smb-bench-public-12__r1", "model": "claude-opus-5-5", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -1110021, "referenceReturnCents": -513970 }, { "cellId": "claude-opus-5-5__smb-bench-public-12__r2", "model": "claude-opus-5-5", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -588255, "referenceReturnCents": -513970 }, { "cellId": "claude-opus-5-5__smb-bench-public-12__r3", "model": "claude-opus-5-5", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -1223408, "referenceReturnCents": -513970 }, { "cellId": "claude-opus-5-5__smb-bench-public-2__r1", "model": "claude-opus-5-5", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": 485183, "referenceReturnCents": 1687477 }, { "cellId": "claude-opus-5-5__smb-bench-public-2__r2", "model": "claude-opus-5-5", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": 1789579, "referenceReturnCents": 1687477 }, { "cellId": "claude-opus-5-5__smb-bench-public-2__r3", "model": "claude-opus-5-5", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": 1398087, "referenceReturnCents": 1687477 }, { "cellId": "claude-opus-5-5__smb-bench-public-3__r1", "model": "claude-opus-5-5", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": -670299, "referenceReturnCents": 1369071 }, { "cellId": "claude-opus-5-5__smb-bench-public-3__r2", "model": "claude-opus-5-5", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": -406362, "referenceReturnCents": 1369071 }, { "cellId": "claude-opus-5-5__smb-bench-public-3__r3", "model": "claude-opus-5-5", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": -364956, "referenceReturnCents": 1369071 }, { "cellId": "claude-opus-5-5__smb-bench-public-4__r1", "model": "claude-opus-5-5", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -885237, "referenceReturnCents": -612846 }, { "cellId": "claude-opus-5-5__smb-bench-public-4__r2", "model": "claude-opus-5-5", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -539084, "referenceReturnCents": -612846 }, { "cellId": "claude-opus-5-5__smb-bench-public-4__r3", "model": "claude-opus-5-5", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -816047, "referenceReturnCents": -612846 }, { "cellId": "claude-opus-5-5__smb-bench-public-5__r1", "model": "claude-opus-5-5", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": -356363, "referenceReturnCents": 61608 }, { "cellId": "claude-opus-5-5__smb-bench-public-5__r2", "model": "claude-opus-5-5", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": -486242, "referenceReturnCents": 61608 }, { "cellId": "claude-opus-5-5__smb-bench-public-5__r3", "model": "claude-opus-5-5", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": -15364, "referenceReturnCents": 61608 }, { "cellId": "claude-opus-5-5__smb-bench-public-6__r1", "model": "claude-opus-5-5", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -460233, "referenceReturnCents": -372926 }, { "cellId": "claude-opus-5-5__smb-bench-public-6__r2", "model": "claude-opus-5-5", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -734664, "referenceReturnCents": -372926 }, { "cellId": "claude-opus-5-5__smb-bench-public-6__r3", "model": "claude-opus-5-5", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -853078, "referenceReturnCents": -372926 }, { "cellId": "claude-opus-5-5__smb-bench-public-7__r1", "model": "claude-opus-5-5", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": 222470, "referenceReturnCents": 814054 }, { "cellId": "claude-opus-5-5__smb-bench-public-7__r2", "model": "claude-opus-5-5", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": -13141, "referenceReturnCents": 814054 }, { "cellId": "claude-opus-5-5__smb-bench-public-7__r3", "model": "claude-opus-5-5", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": -385522, "referenceReturnCents": 814054 }, { "cellId": "claude-opus-5-5__smb-bench-public-8__r1", "model": "claude-opus-5-5", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": -945690, "referenceReturnCents": 572474 }, { "cellId": "claude-opus-5-5__smb-bench-public-8__r2", "model": "claude-opus-5-5", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": -1182260, "referenceReturnCents": 572474 }, { "cellId": "claude-opus-5-5__smb-bench-public-8__r3", "model": "claude-opus-5-5", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": -1391082, "referenceReturnCents": 572474 }, { "cellId": "claude-opus-5-5__smb-bench-public-9__r1", "model": "claude-opus-5-5", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": -104764, "referenceReturnCents": 1826877 }, { "cellId": "claude-opus-5-5__smb-bench-public-9__r2", "model": "claude-opus-5-5", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": 450192, "referenceReturnCents": 1826877 }, { "cellId": "claude-opus-5-5__smb-bench-public-9__r3", "model": "claude-opus-5-5", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": -75740, "referenceReturnCents": 1826877 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-1__r1", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": -502034, "referenceReturnCents": -262165 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-1__r2", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": -430387, "referenceReturnCents": -262165 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-1__r3", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": -362521, "referenceReturnCents": -262165 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-10__r1", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": -2202511, "referenceReturnCents": 885383 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-10__r2", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": -2391379, "referenceReturnCents": 885383 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-10__r3", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": -1313794, "referenceReturnCents": 885383 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-11__r1", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": -580579, "referenceReturnCents": 55721 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-11__r2", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": -601174, "referenceReturnCents": 55721 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-11__r3", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": -817375, "referenceReturnCents": 55721 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-12__r1", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -1229139, "referenceReturnCents": -513970 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-12__r2", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -1156807, "referenceReturnCents": -513970 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-12__r3", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -1392440, "referenceReturnCents": -513970 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-2__r1", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": -9154, "referenceReturnCents": 1687477 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-2__r2", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": -407899, "referenceReturnCents": 1687477 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-2__r3", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": -43880, "referenceReturnCents": 1687477 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-3__r1", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": -967416, "referenceReturnCents": 1369071 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-3__r2", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": -245565, "referenceReturnCents": 1369071 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-3__r3", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": -980634, "referenceReturnCents": 1369071 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-4__r1", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -888163, "referenceReturnCents": -612846 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-4__r2", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -814088, "referenceReturnCents": -612846 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-4__r3", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -779802, "referenceReturnCents": -612846 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-5__r1", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": -651456, "referenceReturnCents": 61608 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-5__r2", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": -617156, "referenceReturnCents": 61608 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-5__r3", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": -607734, "referenceReturnCents": 61608 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-6__r1", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -706518, "referenceReturnCents": -372926 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-6__r2", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -937077, "referenceReturnCents": -372926 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-6__r3", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -890880, "referenceReturnCents": -372926 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-7__r1", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": -595748, "referenceReturnCents": 814054 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-7__r2", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": -267404, "referenceReturnCents": 814054 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-7__r3", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": -150982, "referenceReturnCents": 814054 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-8__r1", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": -524795, "referenceReturnCents": 572474 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-8__r2", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": -889044, "referenceReturnCents": 572474 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-8__r3", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": -1131623, "referenceReturnCents": 572474 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-9__r1", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": -1483925, "referenceReturnCents": 1826877 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-9__r2", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": -1446003, "referenceReturnCents": 1826877 }, { "cellId": "deepseek-v4-1-flash-1017__smb-bench-public-9__r3", "model": "deepseek-v4.1-flash-1017", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": -1317367, "referenceReturnCents": 1826877 }, { "cellId": "gemini-4-argon__smb-bench-public-1__r1", "model": "gemini-4-argon", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": -127099, "referenceReturnCents": -262165 }, { "cellId": "gemini-4-argon__smb-bench-public-1__r2", "model": "gemini-4-argon", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": 105929, "referenceReturnCents": -262165 }, { "cellId": "gemini-4-argon__smb-bench-public-1__r3", "model": "gemini-4-argon", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": 87493, "referenceReturnCents": -262165 }, { "cellId": "gemini-4-argon__smb-bench-public-10__r1", "model": "gemini-4-argon", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": -590125, "referenceReturnCents": 885383 }, { "cellId": "gemini-4-argon__smb-bench-public-10__r2", "model": "gemini-4-argon", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": 199360, "referenceReturnCents": 885383 }, { "cellId": "gemini-4-argon__smb-bench-public-10__r3", "model": "gemini-4-argon", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": -429984, "referenceReturnCents": 885383 }, { "cellId": "gemini-4-argon__smb-bench-public-11__r1", "model": "gemini-4-argon", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": 271399, "referenceReturnCents": 55721 }, { "cellId": "gemini-4-argon__smb-bench-public-11__r2", "model": "gemini-4-argon", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": -917432, "referenceReturnCents": 55721 }, { "cellId": "gemini-4-argon__smb-bench-public-11__r3", "model": "gemini-4-argon", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": 103087, "referenceReturnCents": 55721 }, { "cellId": "gemini-4-argon__smb-bench-public-12__r1", "model": "gemini-4-argon", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -635040, "referenceReturnCents": -513970 }, { "cellId": "gemini-4-argon__smb-bench-public-12__r2", "model": "gemini-4-argon", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -164906, "referenceReturnCents": -513970 }, { "cellId": "gemini-4-argon__smb-bench-public-12__r3", "model": "gemini-4-argon", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -1220435, "referenceReturnCents": -513970 }, { "cellId": "gemini-4-argon__smb-bench-public-2__r1", "model": "gemini-4-argon", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": 931513, "referenceReturnCents": 1687477 }, { "cellId": "gemini-4-argon__smb-bench-public-2__r2", "model": "gemini-4-argon", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": 406770, "referenceReturnCents": 1687477 }, { "cellId": "gemini-4-argon__smb-bench-public-2__r3", "model": "gemini-4-argon", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": 1969444, "referenceReturnCents": 1687477 }, { "cellId": "gemini-4-argon__smb-bench-public-3__r1", "model": "gemini-4-argon", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": -436980, "referenceReturnCents": 1369071 }, { "cellId": "gemini-4-argon__smb-bench-public-3__r2", "model": "gemini-4-argon", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": 1542685, "referenceReturnCents": 1369071 }, { "cellId": "gemini-4-argon__smb-bench-public-3__r3", "model": "gemini-4-argon", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": 505766, "referenceReturnCents": 1369071 }, { "cellId": "gemini-4-argon__smb-bench-public-4__r1", "model": "gemini-4-argon", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -363188, "referenceReturnCents": -612846 }, { "cellId": "gemini-4-argon__smb-bench-public-4__r2", "model": "gemini-4-argon", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -961663, "referenceReturnCents": -612846 }, { "cellId": "gemini-4-argon__smb-bench-public-4__r3", "model": "gemini-4-argon", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -1144484, "referenceReturnCents": -612846 }, { "cellId": "gemini-4-argon__smb-bench-public-5__r1", "model": "gemini-4-argon", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": 350953, "referenceReturnCents": 61608 }, { "cellId": "gemini-4-argon__smb-bench-public-5__r2", "model": "gemini-4-argon", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": 254181, "referenceReturnCents": 61608 }, { "cellId": "gemini-4-argon__smb-bench-public-5__r3", "model": "gemini-4-argon", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": 304093, "referenceReturnCents": 61608 }, { "cellId": "gemini-4-argon__smb-bench-public-6__r1", "model": "gemini-4-argon", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -113333, "referenceReturnCents": -372926 }, { "cellId": "gemini-4-argon__smb-bench-public-6__r2", "model": "gemini-4-argon", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -202742, "referenceReturnCents": -372926 }, { "cellId": "gemini-4-argon__smb-bench-public-6__r3", "model": "gemini-4-argon", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -265257, "referenceReturnCents": -372926 }, { "cellId": "gemini-4-argon__smb-bench-public-7__r1", "model": "gemini-4-argon", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": 396434, "referenceReturnCents": 814054 }, { "cellId": "gemini-4-argon__smb-bench-public-7__r2", "model": "gemini-4-argon", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": 782608, "referenceReturnCents": 814054 }, { "cellId": "gemini-4-argon__smb-bench-public-7__r3", "model": "gemini-4-argon", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": 327803, "referenceReturnCents": 814054 }, { "cellId": "gemini-4-argon__smb-bench-public-8__r1", "model": "gemini-4-argon", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": -100937, "referenceReturnCents": 572474 }, { "cellId": "gemini-4-argon__smb-bench-public-8__r2", "model": "gemini-4-argon", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": -460850, "referenceReturnCents": 572474 }, { "cellId": "gemini-4-argon__smb-bench-public-8__r3", "model": "gemini-4-argon", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": 158321, "referenceReturnCents": 572474 }, { "cellId": "gemini-4-argon__smb-bench-public-9__r1", "model": "gemini-4-argon", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": 1538770, "referenceReturnCents": 1826877 }, { "cellId": "gemini-4-argon__smb-bench-public-9__r2", "model": "gemini-4-argon", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": -855152, "referenceReturnCents": 1826877 }, { "cellId": "gemini-4-argon__smb-bench-public-9__r3", "model": "gemini-4-argon", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": -1414350, "referenceReturnCents": 1826877 }, { "cellId": "glm-5-3__smb-bench-public-1__r1", "model": "glm-5.3", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": -853350, "referenceReturnCents": -262165 }, { "cellId": "glm-5-3__smb-bench-public-1__r2", "model": "glm-5.3", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": -151094, "referenceReturnCents": -262165 }, { "cellId": "glm-5-3__smb-bench-public-1__r3", "model": "glm-5.3", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": -606426, "referenceReturnCents": -262165 }, { "cellId": "glm-5-3__smb-bench-public-10__r1", "model": "glm-5.3", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": -1530889, "referenceReturnCents": 885383 }, { "cellId": "glm-5-3__smb-bench-public-10__r2", "model": "glm-5.3", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": -2463398, "referenceReturnCents": 885383 }, { "cellId": "glm-5-3__smb-bench-public-10__r3", "model": "glm-5.3", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": -2862303, "referenceReturnCents": 885383 }, { "cellId": "glm-5-3__smb-bench-public-11__r1", "model": "glm-5.3", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": -1164153, "referenceReturnCents": 55721 }, { "cellId": "glm-5-3__smb-bench-public-11__r2", "model": "glm-5.3", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": -605995, "referenceReturnCents": 55721 }, { "cellId": "glm-5-3__smb-bench-public-11__r3", "model": "glm-5.3", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": -728896, "referenceReturnCents": 55721 }, { "cellId": "glm-5-3__smb-bench-public-12__r1", "model": "glm-5.3", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -1030259, "referenceReturnCents": -513970 }, { "cellId": "glm-5-3__smb-bench-public-12__r2", "model": "glm-5.3", "task": "smb-bench-public-12", "status": "failed", "businessReturnCents": null, "referenceReturnCents": null }, { "cellId": "glm-5-3__smb-bench-public-12__r3", "model": "glm-5.3", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -1297628, "referenceReturnCents": -513970 }, { "cellId": "glm-5-3__smb-bench-public-2__r1", "model": "glm-5.3", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": -365182, "referenceReturnCents": 1687477 }, { "cellId": "glm-5-3__smb-bench-public-2__r2", "model": "glm-5.3", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": -470905, "referenceReturnCents": 1687477 }, { "cellId": "glm-5-3__smb-bench-public-2__r3", "model": "glm-5.3", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": 113846, "referenceReturnCents": 1687477 }, { "cellId": "glm-5-3__smb-bench-public-3__r1", "model": "glm-5.3", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": -1159938, "referenceReturnCents": 1369071 }, { "cellId": "glm-5-3__smb-bench-public-3__r2", "model": "glm-5.3", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": -1604201, "referenceReturnCents": 1369071 }, { "cellId": "glm-5-3__smb-bench-public-3__r3", "model": "glm-5.3", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": -1546825, "referenceReturnCents": 1369071 }, { "cellId": "glm-5-3__smb-bench-public-4__r1", "model": "glm-5.3", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -1060688, "referenceReturnCents": -612846 }, { "cellId": "glm-5-3__smb-bench-public-4__r2", "model": "glm-5.3", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -1041720, "referenceReturnCents": -612846 }, { "cellId": "glm-5-3__smb-bench-public-4__r3", "model": "glm-5.3", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -774618, "referenceReturnCents": -612846 }, { "cellId": "glm-5-3__smb-bench-public-5__r1", "model": "glm-5.3", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": -474072, "referenceReturnCents": 61608 }, { "cellId": "glm-5-3__smb-bench-public-5__r2", "model": "glm-5.3", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": -810542, "referenceReturnCents": 61608 }, { "cellId": "glm-5-3__smb-bench-public-5__r3", "model": "glm-5.3", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": -692836, "referenceReturnCents": 61608 }, { "cellId": "glm-5-3__smb-bench-public-6__r1", "model": "glm-5.3", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -761268, "referenceReturnCents": -372926 }, { "cellId": "glm-5-3__smb-bench-public-6__r2", "model": "glm-5.3", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -648368, "referenceReturnCents": -372926 }, { "cellId": "glm-5-3__smb-bench-public-6__r3", "model": "glm-5.3", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -951882, "referenceReturnCents": -372926 }, { "cellId": "glm-5-3__smb-bench-public-7__r1", "model": "glm-5.3", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": -641377, "referenceReturnCents": 814054 }, { "cellId": "glm-5-3__smb-bench-public-7__r2", "model": "glm-5.3", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": -857951, "referenceReturnCents": 814054 }, { "cellId": "glm-5-3__smb-bench-public-7__r3", "model": "glm-5.3", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": -1096097, "referenceReturnCents": 814054 }, { "cellId": "glm-5-3__smb-bench-public-8__r1", "model": "glm-5.3", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": -1171978, "referenceReturnCents": 572474 }, { "cellId": "glm-5-3__smb-bench-public-8__r2", "model": "glm-5.3", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": -1162318, "referenceReturnCents": 572474 }, { "cellId": "glm-5-3__smb-bench-public-8__r3", "model": "glm-5.3", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": -500724, "referenceReturnCents": 572474 }, { "cellId": "glm-5-3__smb-bench-public-9__r1", "model": "glm-5.3", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": -2180775, "referenceReturnCents": 1826877 }, { "cellId": "glm-5-3__smb-bench-public-9__r2", "model": "glm-5.3", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": -2189893, "referenceReturnCents": 1826877 }, { "cellId": "glm-5-3__smb-bench-public-9__r3", "model": "glm-5.3", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": -2391626, "referenceReturnCents": 1826877 }, { "cellId": "gpt-6-astra__smb-bench-public-1__r1", "model": "gpt-6-astra", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": 267341, "referenceReturnCents": -262165 }, { "cellId": "gpt-6-astra__smb-bench-public-1__r2", "model": "gpt-6-astra", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": 343129, "referenceReturnCents": -262165 }, { "cellId": "gpt-6-astra__smb-bench-public-1__r3", "model": "gpt-6-astra", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": 213400, "referenceReturnCents": -262165 }, { "cellId": "gpt-6-astra__smb-bench-public-10__r1", "model": "gpt-6-astra", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": 1517721, "referenceReturnCents": 885383 }, { "cellId": "gpt-6-astra__smb-bench-public-10__r2", "model": "gpt-6-astra", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": 1525466, "referenceReturnCents": 885383 }, { "cellId": "gpt-6-astra__smb-bench-public-10__r3", "model": "gpt-6-astra", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": 1561357, "referenceReturnCents": 885383 }, { "cellId": "gpt-6-astra__smb-bench-public-11__r1", "model": "gpt-6-astra", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": 529132, "referenceReturnCents": 55721 }, { "cellId": "gpt-6-astra__smb-bench-public-11__r2", "model": "gpt-6-astra", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": 485836, "referenceReturnCents": 55721 }, { "cellId": "gpt-6-astra__smb-bench-public-11__r3", "model": "gpt-6-astra", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": 337898, "referenceReturnCents": 55721 }, { "cellId": "gpt-6-astra__smb-bench-public-12__r1", "model": "gpt-6-astra", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -109162, "referenceReturnCents": -513970 }, { "cellId": "gpt-6-astra__smb-bench-public-12__r2", "model": "gpt-6-astra", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -631138, "referenceReturnCents": -513970 }, { "cellId": "gpt-6-astra__smb-bench-public-12__r3", "model": "gpt-6-astra", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -405339, "referenceReturnCents": -513970 }, { "cellId": "gpt-6-astra__smb-bench-public-2__r1", "model": "gpt-6-astra", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": 1623233, "referenceReturnCents": 1687477 }, { "cellId": "gpt-6-astra__smb-bench-public-2__r2", "model": "gpt-6-astra", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": 1554946, "referenceReturnCents": 1687477 }, { "cellId": "gpt-6-astra__smb-bench-public-2__r3", "model": "gpt-6-astra", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": 1817822, "referenceReturnCents": 1687477 }, { "cellId": "gpt-6-astra__smb-bench-public-3__r1", "model": "gpt-6-astra", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": 1133633, "referenceReturnCents": 1369071 }, { "cellId": "gpt-6-astra__smb-bench-public-3__r2", "model": "gpt-6-astra", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": 385841, "referenceReturnCents": 1369071 }, { "cellId": "gpt-6-astra__smb-bench-public-3__r3", "model": "gpt-6-astra", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": 1115894, "referenceReturnCents": 1369071 }, { "cellId": "gpt-6-astra__smb-bench-public-4__r1", "model": "gpt-6-astra", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -127170, "referenceReturnCents": -612846 }, { "cellId": "gpt-6-astra__smb-bench-public-4__r2", "model": "gpt-6-astra", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -12061, "referenceReturnCents": -612846 }, { "cellId": "gpt-6-astra__smb-bench-public-4__r3", "model": "gpt-6-astra", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -124306, "referenceReturnCents": -612846 }, { "cellId": "gpt-6-astra__smb-bench-public-5__r1", "model": "gpt-6-astra", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": 568815, "referenceReturnCents": 61608 }, { "cellId": "gpt-6-astra__smb-bench-public-5__r2", "model": "gpt-6-astra", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": 515689, "referenceReturnCents": 61608 }, { "cellId": "gpt-6-astra__smb-bench-public-5__r3", "model": "gpt-6-astra", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": 499104, "referenceReturnCents": 61608 }, { "cellId": "gpt-6-astra__smb-bench-public-6__r1", "model": "gpt-6-astra", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": 333407, "referenceReturnCents": -372926 }, { "cellId": "gpt-6-astra__smb-bench-public-6__r2", "model": "gpt-6-astra", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": 288892, "referenceReturnCents": -372926 }, { "cellId": "gpt-6-astra__smb-bench-public-6__r3", "model": "gpt-6-astra", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": 385894, "referenceReturnCents": -372926 }, { "cellId": "gpt-6-astra__smb-bench-public-7__r1", "model": "gpt-6-astra", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": 667606, "referenceReturnCents": 814054 }, { "cellId": "gpt-6-astra__smb-bench-public-7__r2", "model": "gpt-6-astra", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": 588890, "referenceReturnCents": 814054 }, { "cellId": "gpt-6-astra__smb-bench-public-7__r3", "model": "gpt-6-astra", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": 611283, "referenceReturnCents": 814054 }, { "cellId": "gpt-6-astra__smb-bench-public-8__r1", "model": "gpt-6-astra", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": 107840, "referenceReturnCents": 572474 }, { "cellId": "gpt-6-astra__smb-bench-public-8__r2", "model": "gpt-6-astra", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": 469474, "referenceReturnCents": 572474 }, { "cellId": "gpt-6-astra__smb-bench-public-8__r3", "model": "gpt-6-astra", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": 311822, "referenceReturnCents": 572474 }, { "cellId": "gpt-6-astra__smb-bench-public-9__r1", "model": "gpt-6-astra", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": 1964478, "referenceReturnCents": 1826877 }, { "cellId": "gpt-6-astra__smb-bench-public-9__r2", "model": "gpt-6-astra", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": 989946, "referenceReturnCents": 1826877 }, { "cellId": "gpt-6-astra__smb-bench-public-9__r3", "model": "gpt-6-astra", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": 2277212, "referenceReturnCents": 1826877 }, { "cellId": "gpt-6-1-sol__smb-bench-public-1__r1", "model": "gpt-6.1-sol", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": 268253, "referenceReturnCents": -262165 }, { "cellId": "gpt-6-1-sol__smb-bench-public-1__r2", "model": "gpt-6.1-sol", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": 301533, "referenceReturnCents": -262165 }, { "cellId": "gpt-6-1-sol__smb-bench-public-1__r3", "model": "gpt-6.1-sol", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": 252361, "referenceReturnCents": -262165 }, { "cellId": "gpt-6-1-sol__smb-bench-public-10__r1", "model": "gpt-6.1-sol", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": 1611320, "referenceReturnCents": 885383 }, { "cellId": "gpt-6-1-sol__smb-bench-public-10__r2", "model": "gpt-6.1-sol", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": 1483341, "referenceReturnCents": 885383 }, { "cellId": "gpt-6-1-sol__smb-bench-public-10__r3", "model": "gpt-6.1-sol", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": 2322328, "referenceReturnCents": 885383 }, { "cellId": "gpt-6-1-sol__smb-bench-public-11__r1", "model": "gpt-6.1-sol", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": -478940, "referenceReturnCents": 55721 }, { "cellId": "gpt-6-1-sol__smb-bench-public-11__r2", "model": "gpt-6.1-sol", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": -124475, "referenceReturnCents": 55721 }, { "cellId": "gpt-6-1-sol__smb-bench-public-11__r3", "model": "gpt-6.1-sol", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": -260737, "referenceReturnCents": 55721 }, { "cellId": "gpt-6-1-sol__smb-bench-public-12__r1", "model": "gpt-6.1-sol", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -584140, "referenceReturnCents": -513970 }, { "cellId": "gpt-6-1-sol__smb-bench-public-12__r2", "model": "gpt-6.1-sol", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -872132, "referenceReturnCents": -513970 }, { "cellId": "gpt-6-1-sol__smb-bench-public-12__r3", "model": "gpt-6.1-sol", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -107387, "referenceReturnCents": -513970 }, { "cellId": "gpt-6-1-sol__smb-bench-public-2__r1", "model": "gpt-6.1-sol", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": 1289648, "referenceReturnCents": 1687477 }, { "cellId": "gpt-6-1-sol__smb-bench-public-2__r2", "model": "gpt-6.1-sol", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": 1513013, "referenceReturnCents": 1687477 }, { "cellId": "gpt-6-1-sol__smb-bench-public-2__r3", "model": "gpt-6.1-sol", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": 1167764, "referenceReturnCents": 1687477 }, { "cellId": "gpt-6-1-sol__smb-bench-public-3__r1", "model": "gpt-6.1-sol", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": -1104517, "referenceReturnCents": 1369071 }, { "cellId": "gpt-6-1-sol__smb-bench-public-3__r2", "model": "gpt-6.1-sol", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": -147500, "referenceReturnCents": 1369071 }, { "cellId": "gpt-6-1-sol__smb-bench-public-3__r3", "model": "gpt-6.1-sol", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": 285559, "referenceReturnCents": 1369071 }, { "cellId": "gpt-6-1-sol__smb-bench-public-4__r1", "model": "gpt-6.1-sol", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -204903, "referenceReturnCents": -612846 }, { "cellId": "gpt-6-1-sol__smb-bench-public-4__r2", "model": "gpt-6.1-sol", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -193659, "referenceReturnCents": -612846 }, { "cellId": "gpt-6-1-sol__smb-bench-public-4__r3", "model": "gpt-6.1-sol", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -196958, "referenceReturnCents": -612846 }, { "cellId": "gpt-6-1-sol__smb-bench-public-5__r1", "model": "gpt-6.1-sol", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": 502648, "referenceReturnCents": 61608 }, { "cellId": "gpt-6-1-sol__smb-bench-public-5__r2", "model": "gpt-6.1-sol", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": -51737, "referenceReturnCents": 61608 }, { "cellId": "gpt-6-1-sol__smb-bench-public-5__r3", "model": "gpt-6.1-sol", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": 424673, "referenceReturnCents": 61608 }, { "cellId": "gpt-6-1-sol__smb-bench-public-6__r1", "model": "gpt-6.1-sol", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": 260112, "referenceReturnCents": -372926 }, { "cellId": "gpt-6-1-sol__smb-bench-public-6__r2", "model": "gpt-6.1-sol", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": 149014, "referenceReturnCents": -372926 }, { "cellId": "gpt-6-1-sol__smb-bench-public-6__r3", "model": "gpt-6.1-sol", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -196377, "referenceReturnCents": -372926 }, { "cellId": "gpt-6-1-sol__smb-bench-public-7__r1", "model": "gpt-6.1-sol", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": 659948, "referenceReturnCents": 814054 }, { "cellId": "gpt-6-1-sol__smb-bench-public-7__r2", "model": "gpt-6.1-sol", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": 578004, "referenceReturnCents": 814054 }, { "cellId": "gpt-6-1-sol__smb-bench-public-7__r3", "model": "gpt-6.1-sol", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": 592995, "referenceReturnCents": 814054 }, { "cellId": "gpt-6-1-sol__smb-bench-public-8__r1", "model": "gpt-6.1-sol", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": 222786, "referenceReturnCents": 572474 }, { "cellId": "gpt-6-1-sol__smb-bench-public-8__r2", "model": "gpt-6.1-sol", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": -14424, "referenceReturnCents": 572474 }, { "cellId": "gpt-6-1-sol__smb-bench-public-8__r3", "model": "gpt-6.1-sol", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": -398349, "referenceReturnCents": 572474 }, { "cellId": "gpt-6-1-sol__smb-bench-public-9__r1", "model": "gpt-6.1-sol", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": -165268, "referenceReturnCents": 1826877 }, { "cellId": "gpt-6-1-sol__smb-bench-public-9__r2", "model": "gpt-6.1-sol", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": 1428004, "referenceReturnCents": 1826877 }, { "cellId": "gpt-6-1-sol__smb-bench-public-9__r3", "model": "gpt-6.1-sol", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": 374739, "referenceReturnCents": 1826877 }, { "cellId": "grok-4-7__smb-bench-public-1__r1", "model": "grok-4.7", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": -512383, "referenceReturnCents": -262165 }, { "cellId": "grok-4-7__smb-bench-public-1__r2", "model": "grok-4.7", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": -502572, "referenceReturnCents": -262165 }, { "cellId": "grok-4-7__smb-bench-public-1__r3", "model": "grok-4.7", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": -642325, "referenceReturnCents": -262165 }, { "cellId": "grok-4-7__smb-bench-public-10__r1", "model": "grok-4.7", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": -2170236, "referenceReturnCents": 885383 }, { "cellId": "grok-4-7__smb-bench-public-10__r2", "model": "grok-4.7", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": -1945724, "referenceReturnCents": 885383 }, { "cellId": "grok-4-7__smb-bench-public-10__r3", "model": "grok-4.7", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": -1939903, "referenceReturnCents": 885383 }, { "cellId": "grok-4-7__smb-bench-public-11__r1", "model": "grok-4.7", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": -784487, "referenceReturnCents": 55721 }, { "cellId": "grok-4-7__smb-bench-public-11__r2", "model": "grok-4.7", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": -1000139, "referenceReturnCents": 55721 }, { "cellId": "grok-4-7__smb-bench-public-11__r3", "model": "grok-4.7", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": -871398, "referenceReturnCents": 55721 }, { "cellId": "grok-4-7__smb-bench-public-12__r1", "model": "grok-4.7", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -1291661, "referenceReturnCents": -513970 }, { "cellId": "grok-4-7__smb-bench-public-12__r2", "model": "grok-4.7", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -1456351, "referenceReturnCents": -513970 }, { "cellId": "grok-4-7__smb-bench-public-12__r3", "model": "grok-4.7", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -1470358, "referenceReturnCents": -513970 }, { "cellId": "grok-4-7__smb-bench-public-2__r1", "model": "grok-4.7", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": 20850, "referenceReturnCents": 1687477 }, { "cellId": "grok-4-7__smb-bench-public-2__r2", "model": "grok-4.7", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": 89007, "referenceReturnCents": 1687477 }, { "cellId": "grok-4-7__smb-bench-public-2__r3", "model": "grok-4.7", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": -567831, "referenceReturnCents": 1687477 }, { "cellId": "grok-4-7__smb-bench-public-3__r1", "model": "grok-4.7", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": -970584, "referenceReturnCents": 1369071 }, { "cellId": "grok-4-7__smb-bench-public-3__r2", "model": "grok-4.7", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": -931705, "referenceReturnCents": 1369071 }, { "cellId": "grok-4-7__smb-bench-public-3__r3", "model": "grok-4.7", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": -773625, "referenceReturnCents": 1369071 }, { "cellId": "grok-4-7__smb-bench-public-4__r1", "model": "grok-4.7", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -1044348, "referenceReturnCents": -612846 }, { "cellId": "grok-4-7__smb-bench-public-4__r2", "model": "grok-4.7", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -834490, "referenceReturnCents": -612846 }, { "cellId": "grok-4-7__smb-bench-public-4__r3", "model": "grok-4.7", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -1031714, "referenceReturnCents": -612846 }, { "cellId": "grok-4-7__smb-bench-public-5__r1", "model": "grok-4.7", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": -903852, "referenceReturnCents": 61608 }, { "cellId": "grok-4-7__smb-bench-public-5__r2", "model": "grok-4.7", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": -836356, "referenceReturnCents": 61608 }, { "cellId": "grok-4-7__smb-bench-public-5__r3", "model": "grok-4.7", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": -635969, "referenceReturnCents": 61608 }, { "cellId": "grok-4-7__smb-bench-public-6__r1", "model": "grok-4.7", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -867552, "referenceReturnCents": -372926 }, { "cellId": "grok-4-7__smb-bench-public-6__r2", "model": "grok-4.7", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -953976, "referenceReturnCents": -372926 }, { "cellId": "grok-4-7__smb-bench-public-6__r3", "model": "grok-4.7", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -912275, "referenceReturnCents": -372926 }, { "cellId": "grok-4-7__smb-bench-public-7__r1", "model": "grok-4.7", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": -451279, "referenceReturnCents": 814054 }, { "cellId": "grok-4-7__smb-bench-public-7__r2", "model": "grok-4.7", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": -656775, "referenceReturnCents": 814054 }, { "cellId": "grok-4-7__smb-bench-public-7__r3", "model": "grok-4.7", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": -253113, "referenceReturnCents": 814054 }, { "cellId": "grok-4-7__smb-bench-public-8__r1", "model": "grok-4.7", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": -901651, "referenceReturnCents": 572474 }, { "cellId": "grok-4-7__smb-bench-public-8__r2", "model": "grok-4.7", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": -588042, "referenceReturnCents": 572474 }, { "cellId": "grok-4-7__smb-bench-public-8__r3", "model": "grok-4.7", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": -1384308, "referenceReturnCents": 572474 }, { "cellId": "grok-4-7__smb-bench-public-9__r1", "model": "grok-4.7", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": -1881740, "referenceReturnCents": 1826877 }, { "cellId": "grok-4-7__smb-bench-public-9__r2", "model": "grok-4.7", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": -1865627, "referenceReturnCents": 1826877 }, { "cellId": "grok-4-7__smb-bench-public-9__r3", "model": "grok-4.7", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": -2055666, "referenceReturnCents": 1826877 }, { "cellId": "muse-wonder-1-0__smb-bench-public-1__r1", "model": "muse-wonder-1.0", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": -768887, "referenceReturnCents": -262165 }, { "cellId": "muse-wonder-1-0__smb-bench-public-1__r2", "model": "muse-wonder-1.0", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": -454194, "referenceReturnCents": -262165 }, { "cellId": "muse-wonder-1-0__smb-bench-public-1__r3", "model": "muse-wonder-1.0", "task": "smb-bench-public-1", "status": "valid", "businessReturnCents": -644722, "referenceReturnCents": -262165 }, { "cellId": "muse-wonder-1-0__smb-bench-public-10__r1", "model": "muse-wonder-1.0", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": -3474677, "referenceReturnCents": 885383 }, { "cellId": "muse-wonder-1-0__smb-bench-public-10__r2", "model": "muse-wonder-1.0", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": -942631, "referenceReturnCents": 885383 }, { "cellId": "muse-wonder-1-0__smb-bench-public-10__r3", "model": "muse-wonder-1.0", "task": "smb-bench-public-10", "status": "valid", "businessReturnCents": -3219839, "referenceReturnCents": 885383 }, { "cellId": "muse-wonder-1-0__smb-bench-public-11__r1", "model": "muse-wonder-1.0", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": -830448, "referenceReturnCents": 55721 }, { "cellId": "muse-wonder-1-0__smb-bench-public-11__r2", "model": "muse-wonder-1.0", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": -705978, "referenceReturnCents": 55721 }, { "cellId": "muse-wonder-1-0__smb-bench-public-11__r3", "model": "muse-wonder-1.0", "task": "smb-bench-public-11", "status": "valid", "businessReturnCents": -1285701, "referenceReturnCents": 55721 }, { "cellId": "muse-wonder-1-0__smb-bench-public-12__r1", "model": "muse-wonder-1.0", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -1298437, "referenceReturnCents": -513970 }, { "cellId": "muse-wonder-1-0__smb-bench-public-12__r2", "model": "muse-wonder-1.0", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -1187884, "referenceReturnCents": -513970 }, { "cellId": "muse-wonder-1-0__smb-bench-public-12__r3", "model": "muse-wonder-1.0", "task": "smb-bench-public-12", "status": "valid", "businessReturnCents": -1315464, "referenceReturnCents": -513970 }, { "cellId": "muse-wonder-1-0__smb-bench-public-2__r1", "model": "muse-wonder-1.0", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": -1605053, "referenceReturnCents": 1687477 }, { "cellId": "muse-wonder-1-0__smb-bench-public-2__r2", "model": "muse-wonder-1.0", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": -1519486, "referenceReturnCents": 1687477 }, { "cellId": "muse-wonder-1-0__smb-bench-public-2__r3", "model": "muse-wonder-1.0", "task": "smb-bench-public-2", "status": "valid", "businessReturnCents": -1412633, "referenceReturnCents": 1687477 }, { "cellId": "muse-wonder-1-0__smb-bench-public-3__r1", "model": "muse-wonder-1.0", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": -2299757, "referenceReturnCents": 1369071 }, { "cellId": "muse-wonder-1-0__smb-bench-public-3__r2", "model": "muse-wonder-1.0", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": -2035408, "referenceReturnCents": 1369071 }, { "cellId": "muse-wonder-1-0__smb-bench-public-3__r3", "model": "muse-wonder-1.0", "task": "smb-bench-public-3", "status": "valid", "businessReturnCents": -2320459, "referenceReturnCents": 1369071 }, { "cellId": "muse-wonder-1-0__smb-bench-public-4__r1", "model": "muse-wonder-1.0", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -987349, "referenceReturnCents": -612846 }, { "cellId": "muse-wonder-1-0__smb-bench-public-4__r2", "model": "muse-wonder-1.0", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -938770, "referenceReturnCents": -612846 }, { "cellId": "muse-wonder-1-0__smb-bench-public-4__r3", "model": "muse-wonder-1.0", "task": "smb-bench-public-4", "status": "valid", "businessReturnCents": -885490, "referenceReturnCents": -612846 }, { "cellId": "muse-wonder-1-0__smb-bench-public-5__r1", "model": "muse-wonder-1.0", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": -564089, "referenceReturnCents": 61608 }, { "cellId": "muse-wonder-1-0__smb-bench-public-5__r2", "model": "muse-wonder-1.0", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": -636921, "referenceReturnCents": 61608 }, { "cellId": "muse-wonder-1-0__smb-bench-public-5__r3", "model": "muse-wonder-1.0", "task": "smb-bench-public-5", "status": "valid", "businessReturnCents": -620331, "referenceReturnCents": 61608 }, { "cellId": "muse-wonder-1-0__smb-bench-public-6__r1", "model": "muse-wonder-1.0", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -502237, "referenceReturnCents": -372926 }, { "cellId": "muse-wonder-1-0__smb-bench-public-6__r2", "model": "muse-wonder-1.0", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -862156, "referenceReturnCents": -372926 }, { "cellId": "muse-wonder-1-0__smb-bench-public-6__r3", "model": "muse-wonder-1.0", "task": "smb-bench-public-6", "status": "valid", "businessReturnCents": -1006982, "referenceReturnCents": -372926 }, { "cellId": "muse-wonder-1-0__smb-bench-public-7__r1", "model": "muse-wonder-1.0", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": -660078, "referenceReturnCents": 814054 }, { "cellId": "muse-wonder-1-0__smb-bench-public-7__r2", "model": "muse-wonder-1.0", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": -1115796, "referenceReturnCents": 814054 }, { "cellId": "muse-wonder-1-0__smb-bench-public-7__r3", "model": "muse-wonder-1.0", "task": "smb-bench-public-7", "status": "valid", "businessReturnCents": -780435, "referenceReturnCents": 814054 }, { "cellId": "muse-wonder-1-0__smb-bench-public-8__r1", "model": "muse-wonder-1.0", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": -1872381, "referenceReturnCents": 572474 }, { "cellId": "muse-wonder-1-0__smb-bench-public-8__r2", "model": "muse-wonder-1.0", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": -2021930, "referenceReturnCents": 572474 }, { "cellId": "muse-wonder-1-0__smb-bench-public-8__r3", "model": "muse-wonder-1.0", "task": "smb-bench-public-8", "status": "valid", "businessReturnCents": -1697909, "referenceReturnCents": 572474 }, { "cellId": "muse-wonder-1-0__smb-bench-public-9__r1", "model": "muse-wonder-1.0", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": -2082613, "referenceReturnCents": 1826877 }, { "cellId": "muse-wonder-1-0__smb-bench-public-9__r2", "model": "muse-wonder-1.0", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": -2847681, "referenceReturnCents": 1826877 }, { "cellId": "muse-wonder-1-0__smb-bench-public-9__r3", "model": "muse-wonder-1.0", "task": "smb-bench-public-9", "status": "valid", "businessReturnCents": -2226446, "referenceReturnCents": 1826877 } ], "limits": "Own arithmetic from published source rows, not independently generated model outcomes or a regrading of the simulation. by_model config reports12changed tasks, headline is18task-weighted means. Public dataset metadata and complete486row response retained locally." }