Search operators

brand: benchmark: record: model: metric: date: org:

Separate values with commas, or alternatives with uppercase OR. Example: brand:Meta, Anthropic benchmark:GPQA

Anthropic

Provider prefix
ANTHR
Benchmark Record namespace
002

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-002S46-013 Claude Sonnet 4.6 AA-LCR Overall 57.7% Unknown Primary source ANTHR-S46
BR-002S46-014 Claude Sonnet 4.6 Artificial Analysis Intelligence Index Overall 47.2 Unknown Primary source ANTHR-S46
BR-002S46-015 Claude Sonnet 4.6 GPQA Diamond Accuracy 87.5% Unknown Primary source ANTHR-S46
BR-002S46-016 Claude Sonnet 4.6 Humanity's Last Exam No tools Overall 30% Unknown Primary source ANTHR-S46
BR-002S46-017 Claude Sonnet 4.6 SciCode Overall 46.8% Unknown Primary source ANTHR-S46
BR-002S46-018 Claude Sonnet 4.6 tau2-bench Overall 75.7% Unknown Primary source ANTHR-S46
BR-002S46-019 Claude Sonnet 4.6 tau3-Banking Overall 30.5% Unknown Primary source ANTHR-S46
BR-002S46-020 Claude Sonnet 4.6 Terminal-Bench Hard Overall 53% Unknown Primary source ANTHR-S46
BR-002S46-021 Claude Sonnet 4.6 Terminal-Bench 2.1 Overall 71.2% Unknown Primary source ANTHR-S46
BR-002S46-022 Claude Sonnet 4.6 CritPt Overall 3.1% Unknown Primary source ANTHR-S46
BR-002S46-023 Claude Sonnet 4.6 AA-Omniscience Overall 12.4 Unknown Primary source ANTHR-S46
BR-002S46-024 Claude Sonnet 4.6 AA-Omniscience Accuracy 40% Unknown Primary source ANTHR-S46
BR-002S46-025 Claude Sonnet 4.6 IFBench Overall 56.6% Unknown Primary source ANTHR-S46
BR-002S46-026 Claude Sonnet 4.6 APEX-Agents Overall 28% Unknown Primary source ANTHR-S46
BR-002S46-027 Claude Sonnet 4.6 ITBench SRE Overall 39.8% Unknown Primary source ANTHR-S46
BR-002S46-028 Claude Sonnet 4.6 GDPval-AA Average Normalized Score 43.9% Unknown Primary source ANTHR-S46
BR-002S46-029 Claude Sonnet 4.6 MMMU-Pro Overall 73.3% Unknown Primary source ANTHR-S46
BR-002S46-030 Claude Sonnet 4.6 AA-LCR Overall 70.7% Unknown Primary source ANTHR-S46
BR-002S46-031 Claude Sonnet 4.6 Artificial Analysis Intelligence Index Overall 34.3 Unknown Primary source ANTHR-S46
BR-002S46-032 Claude Sonnet 4.6 GPQA Diamond Accuracy 79.7% Unknown Primary source ANTHR-S46
BR-002S46-033 Claude Sonnet 4.6 Humanity's Last Exam No tools Overall 10.8% Unknown Primary source ANTHR-S46
BR-002S46-034 Claude Sonnet 4.6 SciCode Overall 44.1% Unknown Primary source ANTHR-S46
BR-002S46-035 Claude Sonnet 4.6 tau2-bench Overall 78.9% Unknown Primary source ANTHR-S46
BR-002S46-036 Claude Sonnet 4.6 Terminal-Bench Hard Overall 42.4% Unknown Primary source ANTHR-S46
BR-002S46-037 Claude Sonnet 4.6 CritPt Overall 0.9% Unknown Primary source ANTHR-S46
BR-002S46-038 Claude Sonnet 4.6 AA-Omniscience Overall -1.9 Unknown Primary source ANTHR-S46
BR-002S46-039 Claude Sonnet 4.6 AA-Omniscience Accuracy 36.1% Unknown Primary source ANTHR-S46
BR-002S46-040 Claude Sonnet 4.6 IFBench Overall 42.4% Unknown Primary source ANTHR-S46
BR-002S46-041 Claude Sonnet 4.6 MMMU-Pro Overall 69.2% Unknown Primary source ANTHR-S46
BR-002S46-042 Claude Sonnet 4.6 AA-LCR Overall 58.7% Unknown Primary source ANTHR-S46
BR-002S46-043 Claude Sonnet 4.6 ARC-AGI-1 Overall 86.0% Unknown Primary source ANTHR-S46
BR-002S46-044 Claude Sonnet 4.6 ARC-AGI-2 Overall 58.3% Unknown Primary source ANTHR-S46
BR-002S46-045 Claude Sonnet 4.6 ARC-AGI-1 Overall 86.5% Unknown Primary source ANTHR-S46
BR-002S46-046 Claude Sonnet 4.6 ARC-AGI-2 Overall 60.4% Unknown Primary source ANTHR-S46
BR-002S5-001 Claude Sonnet 5 Artificial Analysis Intelligence Index Overall 53 Unknown Primary source ANTHR-S5
BR-002S5-002 Claude Sonnet 5 DeepSWE Resolved 54% ±4% Unknown Primary source ANTHR-S5
BR-002S5-003 Claude Sonnet 5 GDPval-AA Average Normalized Score 35.9% Unknown Primary source ANTHR-S5
BR-002S5-004 Claude Sonnet 5 GPQA Diamond Accuracy 91.1% Unknown Primary source ANTHR-S5
BR-002S5-005 Claude Sonnet 5 Humanity's Last Exam No tools Overall 39.6% Unknown Primary source ANTHR-S5
BR-002S5-006 Claude Sonnet 5 SciCode Overall 53.6% Unknown Primary source ANTHR-S5
BR-002S5-007 Claude Sonnet 5 tau3-Banking Overall 28.2% Unknown Primary source ANTHR-S5
BR-002S5-008 Claude Sonnet 5 Terminal-Bench 2.1 Overall 80.5% Unknown Primary source ANTHR-S5
BR-002S5-009 Claude Sonnet 5 CritPt Overall 16.9% Unknown Primary source ANTHR-S5
BR-002S5-010 Claude Sonnet 5 AA-Omniscience Overall 15.3 Unknown Primary source ANTHR-S5
BR-002S5-011 Claude Sonnet 5 AA-Omniscience Accuracy 38.3% Unknown Primary source ANTHR-S5
BR-002S5-012 Claude Sonnet 5 GDPval-AA Average Normalized Score 55.4% Unknown Primary source ANTHR-S5
BR-002S5-013 Claude Sonnet 5 MMMU-Pro Overall 77.3% Unknown Primary source ANTHR-S5
BR-002S5-014 Claude Sonnet 5 AA-LCR Overall 70.7% Unknown Primary source ANTHR-S5
BR-002S5-015 Claude Sonnet 5 GDPval-AA Average Normalized Score 50.5% Unknown Primary source ANTHR-S5
BR-002S5-016 Claude Sonnet 5 GDPval-AA Average Normalized Score 45.2% Unknown Primary source ANTHR-S5
BR-002S5-017 Claude Sonnet 5 GPQA Diamond Accuracy 80% Unknown Primary source ANTHR-S5
BR-002S5-018 Claude Sonnet 5 Humanity's Last Exam No tools Overall 17.8% Unknown Primary source ANTHR-S5
BR-002S5-019 Claude Sonnet 5 SciCode Overall 48.6% Unknown Primary source ANTHR-S5
BR-002S5-020 Claude Sonnet 5 tau3-Banking Overall 14% Unknown Primary source ANTHR-S5
BR-002S5-021 Claude Sonnet 5 Terminal-Bench 2.1 Overall 75.3% Unknown Primary source ANTHR-S5
BR-002S5-022 Claude Sonnet 5 CritPt Overall 1.1% Unknown Primary source ANTHR-S5
BR-002S5-023 Claude Sonnet 5 AA-Omniscience Overall -1.2 Unknown Primary source ANTHR-S5
BR-002S5-024 Claude Sonnet 5 AA-Omniscience Accuracy 32.6% Unknown Primary source ANTHR-S5
BR-002S5-025 Claude Sonnet 5 GDPval-AA Average Normalized Score 43.6% Unknown Primary source ANTHR-S5
BR-002S5-026 Claude Sonnet 5 MMMU-Pro Overall 71.9% Unknown Primary source ANTHR-S5
BR-002S5-027 Claude Sonnet 5 AA-LCR Overall 58.7% Unknown Primary source ANTHR-S5
BR-002S5-028 Claude Sonnet 5 GDPval-AA Average Normalized Score 40.2% Unknown Primary source ANTHR-S5
BR-002S5-029 Claude Sonnet 5 CursorBench 3.2 Overall 61.5% Unknown Primary source ANTHR-S5