Anthropic · model
Claude 3 Opus benchmark scores
As of 2026-11-22, Claude 3 Opus (Anthropic) has measured scores on 5 benchmarks and estimated scores on 56 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 48.9% | measured |
| AA-HLE | 2.8% | measured |
| AA-SciCode | 31.1% | estimated ± 3.4 pp, high confidence |
| Artificial Analysis Intelligence Index | 8.7% | measured |
| CritPt | 0.1% | estimated ± 3.4 pp, high confidence |
| GPQA Diamond | 67.6% | estimated ± 2.4 pp, medium confidence |
| HLE | 16.4% | estimated ± 8.5 pp, low confidence |
| LiveCodeBench v6 | 70.8% | estimated ± 4.7 pp, high confidence |
| AA-Omniscience Accuracy | 19.4% | estimated ± 7.3 pp, medium confidence |
| SciCode | 31.8% | estimated ± 4.6 pp, high confidence |
| AA Coding Index | 19.5% | measured |
| BioMysteryBench (human-difficult) | 32.9% | estimated ± 8.3 pp, low confidence |
| SWE-bench Verified | 42.6% | estimated ± 6.5 pp, low confidence |
| SWE-bench Pro | 26.4% | estimated ± 6.0 pp, low confidence |
| MMLU-Pro | 76.6% | estimated ± 5.4 pp, medium confidence |
| FailureSensorIQ | 63.6% | estimated ± 2.1 pp, medium confidence |
| GPQA | 53.3% | estimated ± 6.1 pp, medium confidence |
| MMLU | 83.7% | estimated ± 3.8 pp, high confidence |
| Vals GPQA Diamond | 48.0% | estimated ± 3.2 pp, high confidence |
| Vals LiveCodeBench | 53.1% | estimated ± 7.1 pp, medium confidence |
| Vals MMLU-Pro | 68.1% | estimated ± 3.0 pp, high confidence |
| MMMLU | 77.1% | estimated ± 1.7 pp, medium confidence |
| Chess Puzzles | 4.0% | measured |
| AA MMLU-Pro | 83.5% | estimated ± 1.2 pp, medium confidence |
| ARC-AGI-1 | 72.8% | estimated ± 7.9 pp, low confidence |
| ARC-AGI-2 | 26.1% | estimated ± 14.4 pp, low confidence |
| EBR-bench | 0.5% | estimated ± 12.7 pp, low confidence |
| Furniture Assembly | 24.3% | estimated ± 14.1 pp, low confidence |
| MaxxBench | 30.3% | estimated ± 10.3 pp, low confidence |
| Mystery Game Puzzles | 2.4% | estimated ± 10.3 pp, low confidence |
| NYT Connections | 21.2% | estimated ± 12.6 pp, low confidence |
| Vals SWE-bench | 43.3% | estimated ± 5.5 pp, low confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 48.4% | estimated ± 4.3 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 38.8% | estimated ± 1.1 pp, low confidence |
| FrontierPhysics | 0.0% | estimated ± 6.1 pp, low confidence |
| HLE w/o tools | 22.8% | estimated ± 4.9 pp, high confidence |
| SpireClimb | 0.0% | estimated ± 10.3 pp, low confidence |
| StealthMark | 28.0% | estimated ± 9.7 pp, low confidence |
| ARC-AGI-3 | 1.3% | estimated ± 9.8 pp, low confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| SkillsBench official leaderboard (BenchFlow) | 23.7% | estimated ± 6.2 pp, low confidence |
| Vibe Code Bench | 5.3% | estimated ± 10.0 pp, low confidence |
| FACTS Multimodal | 30.3% | estimated ± 5.6 pp, low confidence |
| ExploitBench | 3.7% | estimated ± 13.4 pp, low confidence |
| C-Eval | 88.2% | estimated ± 1.0 pp, low confidence |
| MMLU-Redux | 89.4% | estimated ± 1.2 pp, low confidence |
| NL2Repo | 11.2% | estimated ± 4.7 pp, medium confidence |
| SuperGPQA | 61.7% | estimated ± 10.1 pp, low confidence |
| AA LiveCodeBench | 84.0% | estimated ± 4.7 pp, low confidence |
| React Native Evals | 69.0% | estimated ± 3.2 pp, medium confidence |
| DAYJOB | 0.4% | estimated ± 6.3 pp, low confidence |
| DAYJOB Healthcare | 0.1% | estimated ± 6.1 pp, low confidence |
| HealthBench (length-adjusted) | 54.1% | estimated ± 3.7 pp, medium confidence |
| HealthBench Professional | 56.7% | estimated ± 4.2 pp, low confidence |
| ScarfBench | 24.4% | estimated ± 9.1 pp, low confidence |
| BlenderWorld (text-only) | 70.6% | estimated ± 4.0 pp, low confidence |
| Cookie-Bench | 72.2% | estimated ± 2.5 pp, low confidence |
| SimpleQA | 12.9% | estimated ± 7.8 pp, medium confidence |
| SEC-Bench Pro | 6.9% | estimated ± 12.3 pp, low confidence |
| BioBasicsBench | 11.1% | estimated ± 10.2 pp, low confidence |
| ExploitBench Internal Port | 0.0% | estimated ± 1.4 pp, low confidence |