Claude Opus 4.7 Max
| Released | 2026-04-16 |
|---|---|
| Price per 1M | $5.00 in · $25.00 out |
| Overall score | 59.0 · rank 126 |
| Context window | 1,000,000 tokens |
| Provider | Anthropic |
| Weights | Proprietary |
| Configuration | Max |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 59.0 | 126 | 23 |
| Overall: Coding | 58.5 | 133 | 16 |
| Overall: Reasoning | 59.8 | 114 | 12 |
| Overall: Agentic work | 59.3 | 119 | 15 |
| Overall: Frontend | 57.2 | 134 | 7 |
| Coding | 58.2 | 125 | 5 |
| Agents | 59.4 | 87 | 4 |
| Reasoning | 60.9 | 109 | 6 |
| Math | 58.1 | 74 | 4 |
| Knowledge | 60.2 | 30 | 2 |
| Frontend | 56.6 | 74 | 1 |
| Multimodal | 57.8 | 50 | 1 |
| Value vs price | +2.3 | 182 |
Evidence
Coding 58.2 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierCode | 38.5% | Epoch AI | 2026-11-11 |
| SciCode | 54.5% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 85.1% | Vals AI | 2026-09-01 |
| SWE-bench Verified (Epoch run) | 83.5% | Epoch AI | 2026-04-20 |
| ProgramBench | 0.0% | Vals AI | 2026-11-09 |
| SWE-bench Verified (Vals run) | 82.0% | Vals AI | 2026-09-01 |
Agents 59.4 ±1.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| OSWorld 2.0 | 18.2% | Epoch AI | 2026-11-11 |
| APEX-Agents | 49.2% | Epoch AI | 2026-11-11 |
| tau2-bench Banking Knowledge | 40.2% | tau2-bench | 2026-07-23 |
| Tax Agent Bench | 23.7% | Vals AI | 2026-11-09 |
Reasoning 60.9 ±2.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 75.8% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 | 92.0% | Epoch AI | 2026-11-11 |
| CritPt | 12.0% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 86.4% | Epoch AI | 2026-08-06 |
| GPQA Diamond (Vals run) | 90.2% | Vals AI | 2026-09-01 |
| Chess Puzzles | 41.0% | Epoch AI | 2026-10-13 |
| Mystery Game Puzzles | 28.0% | Epoch AI | 2026-07-25 |
Math 58.1 ±2.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 70.2% | Epoch AI | 2026-06-10 |
| FrontierMath Tier 4 | 31.7% | Epoch AI | 2026-06-10 |
| ProofBench | 54.0% | Epoch AI | 2026-11-11 |
| OTIS Mock AIME 2024-2025 | 86.7% | Epoch AI | 2026-08-06 |
Knowledge 60.2 ±3.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMLU-Pro (Vals run) | 89.9% | Vals AI | 2026-09-01 |
| Legal Research Bench | 38.5% | Vals AI | 2026-11-09 |
Frontend 56.6 ±0.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 71.0% | Vals AI | 2026-11-09 |
Multimodal 57.8 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 85.5% | Vals AI | 2026-09-01 |
Names matched to this model
claude-opus-4-7-max