Claude Opus 4 benchmark ranking on every AI leaderboard
closed weights · top 10 on 1 of 11 · released May 14, 2025
11 of 11 boards
| Rank | Board | Score | |||
|---|---|---|---|---|---|
| 13 |  MultiChallengeChat · as “claude-4-opus-thinking” | Chat | 58.6% | 29 | |
| 24 | HLEReasoning · as “Claude Opus 4 (Thinking)” | Reasoning | 10.7% | 42 | |
| 31 |  Search ArenaAgents and tools · as “claude-opus-4-search” | Agents and tools | 1,126 | 33 | |
| 46 |  ARC-AGI-2Reasoning · as “Claude Opus 4 (Thinking 16K)” | Reasoning | 8.6% | 78 | |
| 63 | Vision ArenaVision · as “claude-opus-4-20250514-thinking-16k” | Vision | 1,207 | 100 | |
| 82 |  GPQA DiamondReasoning · as “claude-opus-4-20250514_16K” | Reasoning | 76.3% | 100 | |
| 87 | Text ArenaChat · as “claude-opus-4-20250514-thinking-16k” | Chat | 1,426 | 100 | |
| 90 | Epoch ECIReasoning · as “Claude Opus 4” | Reasoning | 142.7 | 100 | |
| 10 |  Aider PolyglotCoding · stale since 2025-10-03 · as “claude-opus-4-20250514 (32k thinking)” | Coding | 72.0% | 50 | |
| 12 |  MMLU-ProReasoning · stale since 2026-03-11 · as “Claude-4-Opus-Thinking” | Reasoning | 87.3% | 100 | |
| 12 |  SWE-bench VerifiedCoding · stale since 2026-02-26 · as “Claude 4 Opus (20250514)” | Coding | 67.6% | 39 |
Category ranks and more models
Sources: each leaderboard's own published results page, captured every day at 04:30 UTC. Scores exactly as each board published them; we run no evaluations. Logos via logo.dev; trademarks belong to their owners.