Claude Opus 4.7 (Medium): benchmark results
Provider: Anthropic. Released 2026-04-16. Access: API.
Aggregate Rating 1741 ± 19, rank #275 of 2205 rated models, from 26 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| DexHoldem Agentic Perception | 34.3 | Strict problem accuracy (%; every applicable field of the pa | 100 |
| DexHoldem Agentic Perception - Opponent Chip Inventory | 43.8 | Field accuracy (%; exact per-denomination count of the oppon | 100 |
| M4Bench - Claude Code native routing Native No-Skill | 0.8 | Task-balanced mean value-column match rate (0–1),28 tasks,5 | 100 |
| M4Bench - Claude Code native routing Native With-Skill | 0.88 | Task-balanced mean value-column match rate (0–1),28 tasks,5 | 100 |
| SGR-Bench - Constraint-Guided | 64.35 | Item-level F1 (%) on the constraint-guided formulation (the | 90 |
| DexHoldem Agentic Perception - Community Cards | 43.6 | Field accuracy (%; visible community cards as an order-insen | 85.7 |
| RepoRef | 63.25 | Success rate (%; exact match of the submitted GitHub issue, | 85.7 |
| SGR-Bench - Row-F1 | 38.51 | Row-level F1 (%) over all tasks: a row counts only when ever | 80 |
| DexHoldem Agentic Perception - Current Bet Chips | 31.2 | Field accuracy (%; exact per-denomination chip counts of the | 78.6 |
| DexHoldem Agentic Perception - Turn Ownership | 93.5 | Field accuracy (%; whose turn it is, all 36 problems; 36 tab | 78.6 |
| DexHoldem Agentic Perception - Robot Chip Inventory | 37.5 | Field accuracy (%; exact per-denomination count of the robot | 71.4 |
| ChainSWE (Oracle) | 64.5 | Per-bug resolution rate (%; share of the 304 bugs in 100 chr | 66.7 |
Interactive version: theaggregate.ai/model?slug=claude-opus-4-7-medium · How It Works · Data refreshed daily, snapshot 2026-11-13.