BENCHMARK REGISTRY
Public Artificial Intelligence Benchmark Records Database

Claude 4.1 Opus

MODEL RECORD: ANTHR-O41

Organization
Anthropic
Family
Claude
Model number
41
Tier
O
Status
ACTIVE
Release date
2025-08-05

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-002O41-001 Claude 4.1 Opus Artificial Analysis Intelligence Index Overall 33.7 Unknown Primary source ANTHR-O41
BR-002O41-002 Claude 4.1 Opus GPQA Diamond Accuracy 80.9% Unknown Primary source ANTHR-O41
BR-002O41-003 Claude 4.1 Opus Humanity's Last Exam No tools Overall 11.9% Unknown Primary source ANTHR-O41
BR-002O41-004 Claude 4.1 Opus SciCode Overall 40.9% Unknown Primary source ANTHR-O41
BR-002O41-005 Claude 4.1 Opus tau2-bench Overall 71.4% Unknown Primary source ANTHR-O41
BR-002O41-006 Claude 4.1 Opus Terminal-Bench Hard Overall 34.3% Unknown Primary source ANTHR-O41
BR-002O41-007 Claude 4.1 Opus CritPt Overall 0% Unknown Primary source ANTHR-O41
BR-002O41-008 Claude 4.1 Opus IFBench Overall 55.4% Unknown Primary source ANTHR-O41
BR-002O41-009 Claude 4.1 Opus MMMU-Pro Overall 67.9% Unknown Primary source ANTHR-O41
BR-002O41-010 Claude 4.1 Opus AA-LCR Overall 66.3% Unknown Primary source ANTHR-O41
BR-002O41-011 Claude 4.1 Opus Artificial Analysis Intelligence Index Overall 28.2 Unknown Primary source ANTHR-O41