Claude Opus 4.8 (Medium): benchmark results
Provider: Anthropic. Released 2026-05-28. Access: API.
Aggregate Rating 1784 ± 20, rank #176 of 2170 rated models, from 30 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BabelArena - ClawEval | 55.8 | Pass^1 (%; ClawEval (service orchestration, multimodal perce | 100 |
| NOLLI - Average | 78.3 | Accuracy (%; 25-task macro average) | 92.9 |
| NOLLI - Cipher - English | 93 | Accuracy (%) | 92.9 |
| NOLLI - Cipher - Korean | 69.3 | Accuracy (%; jamo script) | 92.9 |
| NOLLI - Cryptarithmetic - English | 89.7 | Accuracy (%) | 92.9 |
| NOLLI - Cryptarithmetic - Korean | 95 | Accuracy (%; jamo script) | 92.9 |
| NOLLI - Direct Translations - English | 79.6 | Accuracy (%; eight translated puzzle types) | 92.9 |
| NOLLI - Direct Translations - Korean | 77.4 | Accuracy (%; eight translated puzzle types) | 92.9 |
| NOLLI - Korean Cultural Systems | 77.2 | Accuracy (%; kinship, saju, time and units) | 92.9 |
| NOLLI - Jamo Composition | 47 | Accuracy (%) | 85.7 |
| WeirdML | 76.04 | Average Score | 85.1 |
| CADWorld | 16 | Task success rate (%; 200 long-horizon FreeCAD tasks in 11 w | 83.3 |
Interactive version: theaggregate.ai/model?slug=claude-opus-4-8-medium · How It Works · Data refreshed daily, snapshot 2026-11-05.