Claude 4 Sonnet

MODEL RECORD: ANTHR-S4

Organization
Anthropic
Family
Claude
Model number
4
Tier
S
Status
ACTIVE
Release date
2025-05-22

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-002S4-001 Claude 4 Sonnet Artificial Analysis Intelligence Index Overall 28.9 Unknown Primary source ANTHR-S4
BR-002S4-002 Claude 4 Sonnet GPQA Diamond Accuracy 77.7% Unknown Primary source ANTHR-S4
BR-002S4-003 Claude 4 Sonnet Humanity's Last Exam No tools Overall 9.6% Unknown Primary source ANTHR-S4
BR-002S4-004 Claude 4 Sonnet SciCode Overall 40% Unknown Primary source ANTHR-S4
BR-002S4-005 Claude 4 Sonnet tau2-bench Overall 64.6% Unknown Primary source ANTHR-S4
BR-002S4-006 Claude 4 Sonnet tau3-Banking Overall 13.8% Unknown Primary source ANTHR-S4
BR-002S4-007 Claude 4 Sonnet Terminal-Bench Hard Overall 31.1% Unknown Primary source ANTHR-S4
BR-002S4-008 Claude 4 Sonnet Terminal-Bench 2.1 Overall 36.3% Unknown Primary source ANTHR-S4
BR-002S4-009 Claude 4 Sonnet CritPt Overall 0.3% Unknown Primary source ANTHR-S4
BR-002S4-010 Claude 4 Sonnet AA-Omniscience Overall 0.2 Unknown Primary source ANTHR-S4
BR-002S4-011 Claude 4 Sonnet AA-Omniscience Accuracy 22.3% Unknown Primary source ANTHR-S4
BR-002S4-012 Claude 4 Sonnet IFBench Overall 54.7% Unknown Primary source ANTHR-S4
BR-002S4-013 Claude 4 Sonnet GDPval-AA Average Normalized Score 18% Unknown Primary source ANTHR-S4
BR-002S4-014 Claude 4 Sonnet MMMU-Pro Overall 61.8% Unknown Primary source ANTHR-S4
BR-002S4-015 Claude 4 Sonnet AA-LCR Overall 64.7% Unknown Primary source ANTHR-S4
BR-002S4-016 Claude 4 Sonnet Artificial Analysis Intelligence Index Overall 25.5 Unknown Primary source ANTHR-S4
BR-002S4-017 Claude 4 Sonnet GPQA Diamond Accuracy 68.3% Unknown Primary source ANTHR-S4
BR-002S4-018 Claude 4 Sonnet Humanity's Last Exam No tools Overall 4% Unknown Primary source ANTHR-S4
BR-002S4-019 Claude 4 Sonnet SciCode Overall 37.3% Unknown Primary source ANTHR-S4
BR-002S4-020 Claude 4 Sonnet tau2-bench Overall 52.3% Unknown Primary source ANTHR-S4
BR-002S4-021 Claude 4 Sonnet Terminal-Bench Hard Overall 27.3% Unknown Primary source ANTHR-S4
BR-002S4-022 Claude 4 Sonnet CritPt Overall 1.1% Unknown Primary source ANTHR-S4
BR-002S4-023 Claude 4 Sonnet AA-Omniscience Overall -9.2 Unknown Primary source ANTHR-S4
BR-002S4-024 Claude 4 Sonnet AA-Omniscience Accuracy 22.4% Unknown Primary source ANTHR-S4
BR-002S4-025 Claude 4 Sonnet IFBench Overall 45.4% Unknown Primary source ANTHR-S4
BR-002S4-026 Claude 4 Sonnet MMMU-Pro Overall 62.4% Unknown Primary source ANTHR-S4
BR-002S4-027 Claude 4 Sonnet AA-LCR Overall 44.3% Unknown Primary source ANTHR-S4