Claude Opus 4.7 (High) — benchmark results
Claude Opus 4.7 evaluated at the high reasoning-effort setting. Provider: Anthropic. Released 2026-04-16. Access: API.
Unified ELO 1856 ± 23, rank #100 of 1776 rated models, from 39 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenCompass Code - Comprehensive | 63.7 | Score (%) | 100 |
| OpenCompass LLM - Code | 63.7 | Score (%) | 100 |
| Finance Agent v1.1 | 64.37 | Score (self-reported) | 98.2 |
| OpenCompass Reasoning - Academic | 50.9 | Score (%) | 95.5 |
| Multi-turn Debate (Lechmazur) | 1684.7 | Bradley-Terry Rating | 95 |
| WeirdML | 76.44 | Average Score | 92.7 |
| FutureEval | 14.62 | Unified Forecasting Score | 91.9 |
| OpenCompass LLM - Reasoning | 63.5 | Score (%) | 90.9 |
| Epoch AI - ECI | 156.1 | ECI Score | 89.6 |
| Vals Index | 66.1 | Score (self-reported) | 87.5 |
| OpenCompass LLM - Knowledge | 92.2 | Score (%) | 86.4 |
| Vals Multimodal Index | 67.36 | Score (self-reported) | 84.2 |
Interactive version: theaggregate.ai/model?slug=claude-opus-4-7-high · How the rankings work · Data refreshed daily, snapshot 2026-07-22.