Claude Opus 4.1 (20250805) (Thinking): benchmark results

Claude Opus 4.1 (20250805) evaluated with thinking enabled. Provider: Anthropic. Released 2025-08-05. Access: API.

Aggregate Rating 1687 ± 18, rank #399 of 2168 rated models, from 42 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Vals AI MGSM94.44Accuracy (%)97.6
SEAL - MASK94.2Score95.5
UGI - Writing66.51Writing Score95.5
Vals AI MATH 50095.4Accuracy (%)94.3
UGI - Natural Intelligence58.17NatInt Score91.3
MMLU Pro87.92Score (%)87.1
Vals AI MMLU-Pro87.92Accuracy (%)83.9
MedQA93.59Score (%)77.7
Vals AI MedQA93.59Accuracy (%)77.7
SEAL - VISTA48.44Score73
TaxEval v273.67Score (%)70.2
SEAL Showdown1093Arena Score69.6

Interactive version: theaggregate.ai/model?slug=claude-opus-4-1-20250805-thinking · How It Works · Data refreshed daily, snapshot 2026-10-20.