Claude Opus 4.1 (High): benchmark results

Claude Opus 4.1 evaluated at the high reasoning-effort setting. Provider: Anthropic. Released 2025-08-05. Access: API.

Aggregate Rating 1682 ± 30, rank #441 of 2287 rated models, from 21 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
IKP - T2100Accuracy (%)92.6
IKP - T493.09Accuracy (%)87.9
HAL GAIA68.48Accuracy (%)87.5
HAL GAIA Level 270.93Accuracy (%)87.5
IKP - T398.36Accuracy (%)84.4
HAL SciCode6.92Accuracy (%)80
HAL GAIA Level 353.85Accuracy (%)78.1
HAL SWE-bench Verified Mini54Score (%)76.5
HAL CORE-Bench Hard42.22Accuracy (%)75
IKP - T571.27Accuracy (%)73.7
HAL USACO51.47Accuracy (%)72.7
Incompressible Knowledge Probes (IKP)70.72Mean tier accuracy (%)72

Interactive version: theaggregate.ai/model?slug=claude-opus-4-1-high · How It Works · Data refreshed daily, snapshot 2026-11-22.