Claude Opus 4
| Released | 2025-05-22 |
|---|---|
| Price per 1M | $15.00 in · $75.00 out |
| Overall score | 49.0 · rank 121 |
| Context window | 200,000 tokens |
| Provider | Anthropic |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 49.0 | 121 | 25 |
| Overall: Coding | 49.5 | 113 | 13 |
| Overall: Reasoning | 47.6 | 135 | 13 |
| Overall: Agentic work | 49.4 | 116 | 13 |
| Overall: Frontend | 49.0 | 100 | 8 |
| Coding | 49.5 | 118 | 4 |
| Agents | 49.3 | 109 | 2 |
| Reasoning | 49.8 | 115 | 7 |
| Math | 45.8 | 143 | 4 |
| Knowledge | 45.7 | 112 | 2 |
| General | 53.6 | 76 | 2 |
| Multimodal | 47.6 | 83 | 4 |
| Value vs price | −8.8 | 174 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 47.9 ±1.0 | 23 |
| Thinking | 49.3 ±1.6 | 16 |
Evidence
Coding 49.5 ±1.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Aider Polyglot | 72.0% | Epoch AI | 2026-11-11 |
| GSO | 6.9% | Epoch AI | 2026-11-11 |
| SWE-bench Verified (Epoch run) | 70.7% | Epoch AI | 2026-02-06 |
| LiveCodeBench (Vals run) | 70.2% | Vals AI | 2026-09-01 |
Agents 49.3 ±2.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| METR 50% Time Horizon | $100 | METR | 2026-11-11 |
| METR task suite | 63.9% | Epoch AI | 2026-11-11 |
| DeepResearch Bench | 46.8% | Epoch AI | 2026-11-11 |
Reasoning 49.8 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 8.6% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 8.6% | ARC Prize | 2026-11-11 |
| CritPt | 0.3% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 35.7% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 35.7% | Epoch AI | 2026-11-11 |
| EnigmaEval | 5.6% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 76.3% | Epoch AI | 2025-05-22 |
| GPQA Diamond (Vals run) | 71.7% | Vals AI | 2026-09-01 |
| Kagi Reasoning Benchmark | 74.3% | Kagi | 2026-11-11 |
| SimpleBench | 58.8% | SimpleBench | 2026-11-11 |
| SimpleBench | 58.8% | Epoch AI | 2026-11-11 |
Math 45.8 ±3.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MATH Level 5 | 85.1% | Epoch AI | 2025-05-22 |
| FrontierMath Tiers 1-3 (2025 set) | 4.5% | Epoch AI | 2025-07-04 |
| FrontierMath Tier 4 (2025 set) | 4.2% | Epoch AI | 2025-07-01 |
| OTIS Mock AIME 2024-2025 | 64.4% | Epoch AI | 2025-05-28 |
Knowledge 45.7 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Humanity's Last Exam | 10.7% | Epoch AI | 2026-11-11 |
| MMLU-Pro (Vals run) | 86.2% | Vals AI | 2026-09-01 |
General 53.6 ±2.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| EQ-Bench Creative Writing v3 | 1,578 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,426 | LMArena | 2026-11-09 |
Multimodal 47.6 ±2.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Vision | 1,208 | LMArena | 2026-11-09 |
| MMMU-Pro (Vals run) | 73.3% | Vals AI | 2026-09-01 |
| VPCT | 38.0% | Epoch AI | 2026-11-11 |
| GeoBench | 49.0% | Epoch AI | 2026-11-11 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-1 | 22.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 22.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 | 1.3% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 1.3% | ARC Prize | A stronger configuration result was used |
| Aider Polyglot | 70.7% | Epoch AI | A stronger configuration result was used |
| FrontierMath Tier 4 (2025 set) | 0.0% | Epoch AI | A stronger configuration result was used |
| FrontierMath Tiers 1-3 (2025 set) | 4.1% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond | 69.2% | Epoch AI | A stronger configuration result was used |
| Kagi Reasoning Benchmark | 59.6% | Kagi | A stronger configuration result was used |
| LMArena Text | 1,414 | LMArena | A stronger configuration result was used |
| LMArena Vision | 1,189 | LMArena | A stronger configuration result was used |
| LiveCodeBench (Vals run) | 62.6% | Vals AI | A stronger configuration result was used |
| METR task suite | 61.6% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 42.2% | Epoch AI | A stronger configuration result was used |
| SimpleBench | 58.8% | Epoch AI | A stronger configuration result was used |
| VPCT | 33.0% | Epoch AI | A stronger configuration result was used |
Names matched to this model
claude-opus-4, claude-opus-4-20250514