Claude Opus 4.6 Thinking
| Released | 2026-02-05 |
|---|---|
| Price per 1M | $5.00 in · $25.00 out |
| Overall score | 57.8 · rank 156 |
| Context window | 1,000,000 tokens |
| Provider | Anthropic |
| Weights | Proprietary |
| Configuration | Thinking |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 57.8 | 156 | 14 |
| Overall: Coding | 55.7 | 183 | 8 |
| Overall: Reasoning | 59.3 | 124 | 9 |
| Overall: Agentic work | 57.4 | 168 | 7 |
| Overall: Frontend | 54.0 | 170 | 4 |
| Coding | 55.5 | 171 | 2 |
| Reasoning | 60.7 | 115 | 5 |
| Math | 57.8 | 81 | 3 |
| Knowledge | 59.0 | 44 | 1 |
| Frontend | 52.9 | 102 | 1 |
| General | 61.1 | 47 | 1 |
| Multimodal | 55.9 | 66 | 1 |
| Value vs price | +1.0 | 214 |
Evidence
Coding 55.5 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SWE-bench Verified (Vals run) | 78.2% | Vals AI | 2026-09-01 |
| LiveCodeBench (Vals run) | 84.7% | Vals AI | 2026-09-01 |
Reasoning 60.7 ±1.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 69.2% | Epoch AI | 2026-11-11 |
| Extended NYT Connections | 76.4% | Lech Mazur | 2026-11-10 |
| ARC-AGI-1 | 94.0% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 90.5% | Epoch AI | 2026-02-06 |
| GPQA Diamond (Vals run) | 89.6% | Vals AI | 2026-09-01 |
| Kagi Reasoning Benchmark | 83.6% | Kagi | 2026-11-11 |
Math 57.8 ±2.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 (2025 set) | 40.0% | Epoch AI | 2026-02-06 |
| FrontierMath Tier 4 (2025 set) | 20.8% | Epoch AI | 2026-02-06 |
| OTIS Mock AIME 2024-2025 | 94.4% | Epoch AI | 2026-02-06 |
Knowledge 59.0 ±4.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMLU-Pro (Vals run) | 89.1% | Vals AI | 2026-09-01 |
Frontend 52.9 ±0.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 53.5% | Vals AI | 2026-11-09 |
General 61.1 ±5.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Creative Story-Writing (Lech Mazur) | 66.0% | Lech Mazur | 2026-10-23 |
Multimodal 55.9 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 83.9% | Vals AI | 2026-09-01 |
Names matched to this model
claude-opus-4-6-thinking