Anthropic · model
Claude 3.5 Sonnet benchmark scores
As of 2026-10-07, Claude 3.5 Sonnet (Anthropic) has measured scores on 4 benchmarks and estimated scores on 36 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 57.7% | estimated ± 5.4 pp, medium confidence |
| AA-HLE | 4.9% | estimated ± 6.5 pp, medium confidence |
| AA-SciCode | 32.6% | estimated ± 3.9 pp, high confidence |
| AIME26 | 95.5% | estimated ± 0.6 pp, low confidence |
| Artificial Analysis Intelligence Index | 10.4% | estimated ± 6.2 pp, medium confidence |
| CritPt | 0.6% | estimated ± 4.1 pp, high confidence |
| GPQA Diamond | 59.4% | estimated ± 0.4 pp, high confidence |
| HLE | 7.8% | estimated ± 8.2 pp, low confidence |
| LiveCodeBench v6 | 71.4% | estimated ± 8.1 pp, low confidence |
| AA-Omniscience Accuracy | 16.3% | estimated ± 8.1 pp, medium confidence |
| SciCode | 32.8% | estimated ± 3.8 pp, high confidence |
| AA Coding Index | 23.7% | estimated ± 5.1 pp, medium confidence |
| SWE-bench Verified | 49.0% | measured |
| SWE-bench Pro | 23.8% | estimated ± 3.2 pp, high confidence |
| MMLU-Pro | 71.8% | estimated ± 3.0 pp, high confidence |
| FrontierMath v2 (Tier 4) | 0.0% | measured |
| FrontierMath v2 (Tiers 1-3) | 2.1% | measured |
| GPQA | 59.4% | measured |
| ARC-AGI-1 | 0.0% | estimated ± 6.9 pp, low confidence |
| ARC-AGI-2 | 0.0% | estimated ± 11.6 pp, low confidence |
| FrontierCode 1.1 Main | 0.0% | estimated ± 2.7 pp, low confidence |
| Vals GPQA Diamond | 42.3% | estimated ± 4.8 pp, medium confidence |
| Vals LiveCodeBench | 19.8% | estimated ± 9.9 pp, low confidence |
| Vals MMLU-Pro | 3.0% | estimated ± 1.2 pp, medium confidence |
| Vals SWE-bench | 33.7% | estimated ± 6.8 pp, low confidence |
| HLE w/o tools | 6.2% | estimated ± 4.9 pp, medium confidence |
| Vibe Code Bench | 0.6% | estimated ± 8.1 pp, low confidence |
| C-Eval | 73.0% | estimated ± 0.9 pp, low confidence |
| HMMT Nov 2025 | 99.9% | estimated ± 2.6 pp, low confidence |
| MMAnswerBench | 81.9% | estimated ± 1.3 pp, low confidence |
| MMLU-Redux | 86.6% | estimated ± 2.1 pp, high confidence |
| NL2Repo | 5.2% | estimated ± 6.1 pp, low confidence |
| SuperGPQA | 36.4% | estimated ± 9.2 pp, low confidence |
| HealthBench Hard | 0.0% | estimated ± 5.1 pp, low confidence |
| SWE-Rebench | 57.0% | estimated ± 3.6 pp, low confidence |
| ARC-AGI-3 | 0.0% | estimated ± 2.1 pp, medium confidence |
| FrontierMath (legacy) | 3.2% | estimated ± 0.7 pp, low confidence |
| HealthBench Professional | 6.7% | estimated ± 4.8 pp, low confidence |
| LiveCodeBench | 63.6% | estimated ± 10.2 pp, low confidence |
| MMLU | 86.6% | estimated ± 3.6 pp, medium confidence |