AnthropicAuto-detectedClaude 3 Sonnet
Best configuration ranks #556 of 610 on the BenchLeader Index at 37.9 ±4.7. Last measured 2 Sept 2026. Released 29 Feb 2024.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 200k
- Overall index38
- Reasoning36
- Coding33
- Maths28
- Human preference44
- Multimodal28
- Composite36
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| GPQA Diamond | 40.6%#229 | Epoch AI Benchmarking Hub |
| LMArena Hard Prompts | 1282#246 | LMArena |
| GPQA Diamond (AA)not in index | 40.0%#454 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 3.6%#496 | Artificial Analysis |
Coding
| Benchmark | default | Source |
|---|---|---|
| WeirdML | 10.2%#144 | WeirdML |
| LMArena Coding | 1318#238 | LMArena |
Maths
| Benchmark | default | Source |
|---|---|---|
| OTIS Mock AIME | 2.5%#236 | Epoch AI Benchmarking Hub |
| MATH Level 5 | 18.2%#74 | Epoch AI Benchmarking Hub |
Human preference
| Benchmark | default | Source |
|---|---|---|
| LMArena Text | 1281#247 | LMArena |
Multimodal
| Benchmark | default | Source |
|---|---|---|
| LMArena Vision | 984#128 | LMArena |
| MMMU (validation) | 53.1%#39 | MMMU |
Composite
| Benchmark | default | Source |
|---|---|---|
| Epoch Capabilities Indexnot in index | 120.7#160 | Epoch AI Benchmarking Hub |
| AA Intelligence Index | 5.9#465 | Artificial Analysis |
See also
Data as of 9 Sept 2026. Compare with another model.