Claude Opus 4.6
| Released | 2026-02-05 |
|---|---|
| Price per 1M | $5.00 in · $25.00 out |
| Overall score | 58.4 · rank 47 |
| Context window | 1,000,000 tokens |
| Provider | Anthropic |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 58.4 | 47 | 39 |
| Overall: Coding | 57.3 | 55 | 24 |
| Overall: Reasoning | 59.1 | 44 | 18 |
| Overall: Agentic work | 58.5 | 51 | 22 |
| Overall: Frontend | 55.1 | 60 | 9 |
| Coding | 57.2 | 55 | 5 |
| Agents | 58.6 | 44 | 7 |
| Reasoning | 60.7 | 38 | 10 |
| Math | 57.9 | 44 | 5 |
| Knowledge | 57.4 | 45 | 3 |
| Frontend | 53.7 | 61 | 2 |
| General | 61.4 | 22 | 5 |
| Multimodal | 57.9 | 30 | 2 |
| Value vs price | +3.7 | 90 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 57.3 ±1.0 | 19 |
| High | 58.8 ±1.8 | 10 |
| Low | 55.0 ±6.7 | 4 |
| Max | 57.9 ±1.5 | 17 |
| Medium | 58.8 ±5.4 | 3 |
| Non-reasoning | 51.5 ±6.4 | 1 |
| Thinking | 57.7 ±1.9 | 14 |
Evidence
Coding 57.2 ±1.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierCode | 26.6% | Epoch AI | 2026-11-11 |
| MirrorCode | 33.3% | Epoch AI | 2026-10-21 |
| GSO | 41.2% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 84.7% | Vals AI | 2026-09-01 |
| SWE-bench Verified (Epoch run) | 78.7% | Epoch AI | 2026-02-18 |
| SWE-bench Verified (Vals run) | 78.2% | Vals AI | 2026-09-01 |
Agents 58.6 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| APEX-Agents | 46.3% | Epoch AI | 2026-11-11 |
| Terminal-Bench 2.0 | 79.8% | Epoch AI | 2026-03-12 |
| Remote Labor Index | 4.2% | Epoch AI | 2026-11-11 |
| METR 50% Time Horizon | $719 | METR | 2026-11-11 |
| tau2-bench Banking Knowledge | 27.3% | tau2-bench | 2026-05-06 |
| METR task suite | 78.9% | Epoch AI | 2026-11-11 |
| DeepResearch Bench | 55.3% | Epoch AI | 2026-11-11 |
| Vending-Bench 2 | $8,018 | Epoch AI | 2026-11-11 |
Reasoning 60.7 ±1.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 69.2% | Epoch AI | 2026-11-11 |
| Extended NYT Connections | 92.1% | Lech Mazur | 2026-11-10 |
| ARC-AGI-2 (ARC Prize verified) | 69.2% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 94.0% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 94.0% | Epoch AI | 2026-11-11 |
| EnigmaEval | 7.6% | 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 |
| ARC-AGI-3 | 0.5% | ARC Prize | 2026-11-11 |
| Kagi Reasoning Benchmark | 83.6% | Kagi | 2026-11-11 |
| Chess Puzzles | 21.0% | Epoch AI | 2026-10-13 |
| SimpleBench | 67.6% | SimpleBench | 2026-02-17 |
| SimpleBench | 67.6% | Epoch AI | 2026-11-11 |
| Mystery Game Puzzles | 25.0% | Epoch AI | 2026-07-25 |
Math 57.9 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 66.0% | Epoch AI | 2026-06-11 |
| FrontierMath Tier 4 | 26.8% | Epoch AI | 2026-06-11 |
| ProofBench | 50.0% | Epoch AI | 2026-11-11 |
| OTIS Mock AIME 2024-2025 | 94.4% | Epoch AI | 2026-02-06 |
| MathArena Final-Answer Competitions | 78.5% | MathArena | 2026-11-11 |
| FrontierMath Tiers 1-3 (2025 set) | 40.7% | Epoch AI | 2026-02-12 |
| FrontierMath Tier 4 (2025 set) | 22.9% | Epoch AI | 2026-02-12 |
Knowledge 57.4 ±2.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 47.0% | Epoch AI | 2026-08-27 |
| Humanity's Last Exam | 34.4% | Epoch AI | 2026-11-11 |
| MMLU-Pro (Vals run) | 89.1% | Vals AI | 2026-09-01 |
Frontend 53.7 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 57.6% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,546 | LMArena | 2026-11-09 |
General 61.4 ±1.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| EQ-Bench 4 | 1,210 | EQ-Bench | 2026-10-24 |
| EQ-Bench Creative Writing v3 | 1,810 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,503 | LMArena | 2026-11-09 |
| Creative Story-Writing (Lech Mazur) | 66.0% | Lech Mazur | 2026-10-23 |
| EQ-Bench Longform Creative Writing | 77.7% | EQ-Bench | 2026-11-11 |
Multimodal 57.9 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 83.9% | Vals AI | 2026-09-01 |
| LMArena Vision | 1,299 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-1 (ARC Prize verified) | 93.0% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 86.0% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 92.0% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 68.8% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 64.6% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 66.3% | ARC Prize | A stronger configuration result was used |
| DeepResearch Bench | 51.4% | Epoch AI | A stronger configuration result was used |
| DeepResearch Bench | 53.2% | Epoch AI | A stronger configuration result was used |
| EnigmaEval | 6.8% | Epoch AI | A stronger configuration result was used |
| Extended NYT Connections | 76.4% | Lech Mazur | A stronger configuration result was used |
| Extended NYT Connections | 43.2% | Lech Mazur | A stronger configuration result was used |
| FrontierMath Tier 4 (2025 set) | 14.6% | Epoch AI | A stronger configuration result was used |
| FrontierMath Tier 4 (2025 set) | 20.8% | Epoch AI | A stronger configuration result was used |
| FrontierMath Tiers 1-3 (2025 set) | 38.3% | Epoch AI | A stronger configuration result was used |
| FrontierMath Tiers 1-3 (2025 set) | 40.0% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond | 88.4% | Epoch AI | A stronger configuration result was used |
| GSO | 33.3% | Epoch AI | A stronger configuration result was used |
| Humanity's Last Exam | 19.0% | Epoch AI | A stronger configuration result was used |
| Kagi Reasoning Benchmark | 72.4% | Kagi | A stronger configuration result was used |
| LMArena Text | 1,496 | LMArena | A stronger configuration result was used |
| LMArena Vision | 1,293 | LMArena | A stronger configuration result was used |
| LMArena WebDev | 1,537 | LMArena | A stronger configuration result was used |
| Mystery Game Puzzles | 15.0% | Epoch AI | A stronger configuration result was used |
| Mystery Game Puzzles | 7.0% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 91.1% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 76.4% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 75.3% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 74.7% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 72.1% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 71.9% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 69.9% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 66.9% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 66.5% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 62.9% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 58.0% | Epoch AI | A stronger configuration result was used |
| Vibe Code Bench v1.1 | 53.5% | Vals AI | A stronger configuration result was used |
Names matched to this model
anthropic-opus-4-6, claude-opus-4-6