Claude 3.7 Sonnet benchmark ranking on every AI leaderboard
closed weights · top 10 on 0 of 9 · released Feb 24, 2025
9 of 9 boards
| Rank | Board | Score | |||
|---|---|---|---|---|---|
| 21 |  MultiChallengeChat · as “claude-3-7-sonnet-thinking” | Chat | 51.6% | 29 | |
| 29 | HLEReasoning · as “Claude 3.7 Sonnet (Thinking)” | Reasoning | 8.0% | 42 | |
| 64 |  ARC-AGI-2Reasoning · as “Claude 3.7 (8K)” | Reasoning | 0.9% | 78 | |
| 72 |  Vision ArenaVision · as “claude-3-7-sonnet-20250219-thinking-32k” | Vision | 1,193 | 100 | |
| 73 |  GPQA DiamondReasoning · as “claude-3-7-sonnet-20250219_64K” | Reasoning | 79.7% | 100 | |
| 100 | Epoch ECIReasoning · as “Claude 3.7 Sonnet” | Reasoning | 141.2 | 100 | |
| 13 |  Aider PolyglotCoding · stale since 2025-10-03 · as “claude-3-7-sonnet-20250219 (32k thinking tokens)” | Coding | 64.9% | 50 | |
| 28 |  SWE-bench VerifiedCoding · stale since 2026-02-26 · as “Claude 3.7 Sonnet (20250219)” | Coding | 52.8% | 39 | |
| 39 |  MMLU-ProReasoning · stale since 2026-03-11 · as “Claude-3.7-Sonnet-Thinking” | Reasoning | 84.0% | 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.