Claude Sonnet 4 benchmark ranking on every AI leaderboard
closed weights · top 10 on 0 of 9 · released May 14, 2025
9 of 9 boards
| Rank | Board | Score | |||
|---|---|---|---|---|---|
| 15 |  MultiChallengeChat · as “claude-4-sonnet-thinking” | Chat | 57.1% | 29 | |
| 31 | HLEReasoning · as “Claude Sonnet 4 (Thinking)” | Reasoning | 7.8% | 42 | |
| 49 |  ARC-AGI-2Reasoning · as “Claude Sonnet 4 (Thinking 16K)” | Reasoning | 5.9% | 78 | |
| 64 |  Vision ArenaVision · as “claude-sonnet-4-20250514-thinking-32k” | Vision | 1,206 | 100 | |
| 75 |  GPQA DiamondReasoning · as “claude-sonnet-4-20250514_59K” | Reasoning | 79.2% | 100 | |
| 97 | Epoch ECIReasoning · as “Claude Sonnet 4” | Reasoning | 141.7 | 100 | |
| 16 |  Aider PolyglotCoding · stale since 2025-10-03 · as “claude-sonnet-4-20250514 (32k thinking)” | Coding | 61.3% | 50 | |
| 17 |  SWE-bench VerifiedCoding · stale since 2026-02-26 · as “Claude 4 Sonnet (20250514)” | Coding | 64.9% | 39 | |
| 41 |  MMLU-ProReasoning · stale since 2026-03-11 · as “Claude-4-Sonnet” | Reasoning | 83.7% | 100 |
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.