Claude Opus 4.1 (Non-reasoning): benchmark results

Claude Opus 4.1 evaluated with reasoning disabled. Provider: Anthropic. Released 2025-08-05. Access: API.

Aggregate Rating 1666 ± 29, rank #486 of 2257 rated models, from 14 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Generalization V1 (Lechmazur)1.69Avg Rank (lower is better)98.8
UGI - Writing69.91Writing Score98
UGI - Natural Intelligence58.74NatInt Score91.8
Confabulation Leaderboard (Lechmazur)3.96Confabulation rate % (lower is better)91.5
Elimination Game (Lechmazur)5.21TrueSkill μ84.7
MeasureBench Synthetic13.3Accuracy (%)75
Translation (Lechmazur)8.56Mean Score71.4
NYT Connections Older Models21.7Score (%)63.4
MeasureBench Real-world14.3Accuracy (%)58.3
Chess Bench LLM303Lichess-Classical-calibrated Glicko-2 rating (native signed 45.3
Inverse Turing Bench57.99Accuracy (imported)42.9
Step Game (Lechmazur)1.57TrueSkill μ40.5

Interactive version: theaggregate.ai/model?slug=claude-opus-4-1-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-17.