Claude Opus 4.8 (Adaptive Reasoning, Max Effort) — benchmark results
Claude Opus 4.8 evaluated in adaptive-reasoning mode at max effort. Provider: Anthropic. Released 2026-05-29. Access: API.
Unified ELO 1965 ± 36, rank #37 of 1776 rated models, from 40 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Humanity's Last Exam | 45.74 | Accuracy (%) | 99.6 |
| AA Omniscience | 27.43 | Score | 99.6 |
| AA Omniscience - Software Engineering (SWE) - Swift | 88 | Accuracy (%) | 99.3 |
| Artificial Analysis Intelligence Index | 55.69 | Intelligence Index | 99.1 |
| AA Omniscience - Software Engineering (SWE) - Go | 80 | Accuracy (%) | 98 |
| AA Terminal-Bench Hard | 58.33 | Accuracy (%) | 97.9 |
| AA Omniscience - Software Engineering (SWE) - HTML | 82 | Accuracy (%) | 97.7 |
| AA Omniscience - Software Engineering (SWE) - Rust | 82 | Accuracy (%) | 97.5 |
| AA Omniscience - Software Engineering (SWE) - Dart | 68 | Accuracy (%) | 97.1 |
| AA GPQA Diamond | 92.02 | Accuracy (%) | 96.8 |
| AA Omniscience - Software Engineering (SWE) - JavaScript | 81.82 | Accuracy (%) | 96.8 |
| UGI - Natural Intelligence | 65.39 | NatInt Score | 96.8 |
Interactive version: theaggregate.ai/model?slug=claude-opus-4-8-adaptive-reasoning-max-effort · How the rankings work · Data refreshed daily, snapshot 2026-07-22.