Claude Opus 4
Claude / Anthropic
37scores
28benchmarks
$15 / $75 per 1M tokenscost in/out
Metadata
Claude Closed/API
Aliases: anthropic-claude-4-opus-20250522, anthropic-claude-opus-4, anthropic/claude-4-opus-20250522, anthropic/claude-opus-4, claude-4-opus-20250522, claude-opus-4
| Benchmark | Category | Rank | Score | Sampled |
|---|---|---|---|---|
| ARC-AGI-1 | Agentic | 84 | 35.67 | 2026-05-05 |
| ARC-AGI-1 | Agentic | 92 | 30.67 | 2026-05-05 |
| ARC-AGI-1 | Agentic | 99 | 27 | 2026-05-05 |
| ARC-AGI-1 | Agentic | 105 | 22.50 | 2026-05-05 |
| ARC-AGI-2 | Agentic | 53 | 8.61 | 2026-05-05 |
| ARC-AGI-2 | Agentic | 70 | 4.52 | 2026-05-05 |
| ARC-AGI-2 | Agentic | 110 | 1.27 | 2026-05-05 |
| ARC-AGI-2 | Agentic | 138 | 0 | 2026-05-05 |
| LiveCodeBench | Coding | 19 | 56.60 | 2026-05-06 |
| LiveCodeBench | Coding | 22 | 46.90 | 2026-05-06 |
| LiveCodeBench | Coding | 74 | 62.629% | 2026-05-28 |
| GSMA Open Telco Leaderboard | Domain | 12 | 68.25 | 2026-05-06 |
| TutorBench | Education | 21 | 45.46 | 2026-05-06 |
| FinanceArena | Finance | 6 | 44.6 | 2026-05-27 |
| MortgageTax | Finance | 47 | 58.586% | 2026-05-28 |
| TaxEval v2 | Finance | 47 | 71.914% | 2026-05-28 |
| Xent Games | Game | 7 | 58.35 overall | 2026-05-28 |
| MedQA | Healthcare | 27 | 92.867% | 2026-04-16 |
| HUMAINE | Human Preference | 25 | 3.50 | 2026-05-06 |
| AIIQ Composite IQ | Intelligence | 32 | 100 | 2026-05-12 |
| GPQA Diamond | Intelligence | 64 | 71.717% | 2026-05-28 |
| MMLU Pro | Intelligence | 28 | 86.166% | 2026-05-28 |
| MMMU Pro | Intelligence | 40 | 73.31% | 2026-05-28 |
| AraGen v3 | Language | 4 | 80.96 | 2026-05-06 |
| HindiGen v1 | Language | 5 | 74.49 | 2026-05-06 |
| LegalBench | Legal | 33 | 83.071% | 2026-05-28 |
| AIME | Math | 69 | 41.25% | 2026-04-16 |
| IneqMath | Math | 28 | 5.50 | 2026-05-06 |
| MATH 500 | Math | 24 | 90.4% | 2026-01-09 |
| MGSM | Math | 8 | 93.782% | 2026-01-09 |
| Design Arena | Multimodal | 53 | 1219 | 2026-05-06 |
| Visual-Language Understanding | Multimodal | 17 | 46.96 | 2026-05-06 |
| Visual-Language Understanding | Multimodal | 29 | 43.53 | 2026-05-06 |
| ARC-AGI v2 | Reasoning | 13 | 0.09 | 2026-05-06 |
| EnigmaEval | Reasoning | 13 | 5.57 | 2026-05-06 |
| EnigmaEval | Reasoning | 23 | 3.21 | 2026-05-06 |
| Humanity's Last Exam (Text Only) | Reasoning | 26 | 10.80 | 2026-05-06 |
No matching rows.