Claude Opus 4.7 (Non-reasoning): benchmark results

Provider: Anthropic. Released 2026-04-16. Access: API.

Aggregate Rating 1711 ± 24, rank #356 of 2286 rated models, from 16 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
ALE-Bench1323.05Performance (Self-Refine x1) (imported)92.2
WeirdML76.4Average Score85.1
CoffeeBench2781.93Mean net income ($)83.3
AstroAlertBench48.87End-to-end five-class accuracy (%; 1,500 ZTF alerts, 300 eac72.7
BenchCAD 1.0 - Code Edit0.81Accuracy (0 to 1, share of the original-to-target IoU gap th66.7
TUA-Bench49.7Success rate (%; mean of the verifier's scalar task reward o66.7
DGEval - Regulatory Recall17.4Accuracy (%)61.8
BenchCAD 1.0 - Code QA0.8Total accuracy (0 to 1) on 2,400 numeric CAD questions from 55.6
BenchCAD 1.0 - Vision QA0.53Total accuracy (0 to 1) on 2,400 numeric CAD questions from 50
DGEval - IMDG Code MCQ65.8Accuracy (%)38.2
BenchCAD 1.0 - Vision2Code0.26IoU-score (voxel IoU x execution rate, 0 to 1), image to Cad36.4
Generalization V2 (Lechmazur)52.6Inverse-Rank Score34.5

Interactive version: theaggregate.ai/model?slug=claude-opus-4-7-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-20.