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 1675 ± 1, rank #164 of 1761 rated models, from 30 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Terminal-Bench Hard | 58.33 | Accuracy (%) | 97.9 |
| AA Humanity's Last Exam | 48.66 | Accuracy (%) | 97.2 |
| AA Omniscience | 28.75 | Score | 96.3 |
| UGI - Writing | 65.88 | Writing Score | 96.2 |
| UGI - Natural Intelligence | 65.39 | NatInt Score | 96.1 |
| Artificial Analysis Intelligence Index | 46.44 | Intelligence Index | 94.9 |
| AA Omniscience - Software Engineering (SWE) | 75.4 | Accuracy (%) | 94 |
| UGI Leaderboard | 52.64 | UGI Score | 94 |
| AA CritPt | 20.86 | Accuracy (%) | 93.3 |
| AA GPQA Diamond | 92.02 | Accuracy (%) | 93.3 |
| AA TAU-2 Bench | 94.44 | Accuracy (%) | 92.9 |
| AA Omniscience - Health | 44.57 | Accuracy (%) | 92.4 |
Interactive version: theaggregate.ai/model?slug=claude-opus-4-8-adaptive-reasoning-max-effort · How It Works · Data refreshed daily, snapshot 2026-09-05.