Claude Opus 4 (Thinking 16K): benchmark results
Claude Opus 4 evaluated with a 16K-token thinking budget. Provider: Anthropic. Released 2025-05-22. Access: API.
Aggregate Rating 1666 ± 28, rank #472 of 2168 rated models, from 45 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Generalization V1 (Lechmazur) | 1.69 | Avg Rank (lower is better) | 98.8 |
| Confabulation Leaderboard (Lechmazur) | 2.48 | Confabulation rate % (lower is better) | 98.5 |
| Chatbot Arena (Text - Longer Query) | 1466 | Arena Score | 83.8 |
| Chatbot Arena (Text - Creative Writing) | 1433 | Arena Score | 83.5 |
| Chatbot Arena (Text - Instruction Following) | 1444 | Arena Score | 82.2 |
| Chatbot Arena (Text - Entertainment, Sports & Media) | 1422 | Arena Score | 81.8 |
| Chatbot Arena (Text - Writing, Literature & Language) | 1432 | Arena Score | 81.8 |
| Chatbot Arena (Text - Coding) | 1498 | Arena Score | 80.1 |
| BAZAAR (Lechmazur) | 6.86 | TrueSkill μ | 80 |
| Chatbot Arena (Text - German) | 1451 | Arena Score | 78.1 |
| Chatbot Arena (Text - Russian) | 1441 | Arena Score | 76.8 |
| Chatbot Arena (Text - Hard Prompts) | 1457 | Arena Score | 74.8 |
Interactive version: theaggregate.ai/model?slug=claude-opus-4-thinking-16k · How It Works · Data refreshed daily, snapshot 2026-10-20.