Claude Opus 4.5
| Released | 2025-11-24 |
|---|---|
| Price per 1M | $5.00 in · $25.00 out |
| Overall score | 55.2 · rank 73 |
| Context window | 200,000 tokens |
| Provider | Anthropic |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 55.2 | 73 | 40 |
| Overall: Coding | 54.7 | 73 | 27 |
| Overall: Reasoning | 54.8 | 79 | 16 |
| Overall: Agentic work | 55.9 | 71 | 25 |
| Overall: Frontend | 49.7 | 91 | 9 |
| Coding | 56.6 | 61 | 4 |
| Agents | 55.6 | 71 | 12 |
| Reasoning | 55.9 | 79 | 9 |
| Math | 53.5 | 82 | 4 |
| Knowledge | 54.7 | 64 | 3 |
| Frontend | 45.9 | 88 | 2 |
| General | 58.5 | 38 | 3 |
| Multimodal | 52.1 | 64 | 3 |
| Value vs price | +0.6 | 116 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 54.3 ±1.3 | 25 |
| High | 54.5 ±1.4 | 13 |
| Low | 57.1 ±7.9 | 1 |
| Non-reasoning | 52.5 ±6.4 | 1 |
| Thinking | 54.1 ±1.5 | 19 |
Evidence
Coding 56.6 ±1.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| WeirdML v3 | 6.5% | Epoch AI | 2026-11-11 |
| GSO | 26.5% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 83.7% | Vals AI | 2026-09-01 |
| SWE-bench Verified (Epoch run) | 76.7% | Epoch AI | 2026-02-05 |
| SWE-bench Verified (Vals run) | 76.4% | Vals AI | 2026-09-01 |
Agents 55.6 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 2.0 | 63.2% | Epoch AI | 2025-11-24 |
| Remote Labor Index | 3.8% | Epoch AI | 2026-11-11 |
| METR 50% Time Horizon | $293 | METR | 2026-11-11 |
| tau2-bench Banking Knowledge | 24.7% | tau2-bench | 2026-05-05 |
| BFCL v4 | 77.5% | BFCL | 2026-04-12 |
| METR task suite | 75.0% | Epoch AI | 2026-11-11 |
| OSWorld (v1) | 66.3% | Epoch AI | 2026-11-11 |
| tau2-bench Airline | 84.0% | tau2-bench | 2026-05-05 |
| DeepResearch Bench | 54.8% | Epoch AI | 2026-11-11 |
| BALROG | 43.5% | Epoch AI | 2026-11-11 |
| Vending-Bench 2 | $4,967 | Epoch AI | 2026-11-11 |
| tau2-bench Telecom | 92.3% | tau2-bench | 2026-05-05 |
| tau2-bench Retail | 79.6% | tau2-bench | 2026-05-05 |
Reasoning 55.9 ±1.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 37.6% | Epoch AI | 2026-11-11 |
| Extended NYT Connections | 52.5% | Lech Mazur | 2026-11-10 |
| ARC-AGI-1 | 80.0% | Epoch AI | 2026-11-11 |
| EnigmaEval | 11.9% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 86.1% | Epoch AI | 2025-11-24 |
| GPQA Diamond (Vals run) | 85.9% | Vals AI | 2026-09-01 |
| Kagi Reasoning Benchmark | 70.7% | Kagi | 2026-11-11 |
| Chess Puzzles | 14.0% | Epoch AI | 2026-10-13 |
| SimpleBench | 62.0% | SimpleBench | 2025-11-20 |
| SimpleBench | 62.0% | Epoch AI | 2026-11-11 |
| Mystery Game Puzzles | 22.0% | Epoch AI | 2026-07-25 |
Math 53.5 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tier 4 | 4.9% | Epoch AI | 2026-06-11 |
| FrontierMath Tiers 1-3 | 34.4% | Epoch AI | 2026-06-11 |
| ProofBench | 36.0% | Epoch AI | 2026-11-11 |
| OTIS Mock AIME 2024-2025 | 86.1% | Epoch AI | 2025-11-24 |
| FrontierMath Tiers 1-3 (2025 set) | 20.7% | Epoch AI | 2025-11-25 |
| FrontierMath Tier 4 (2025 set) | 4.2% | Epoch AI | 2025-11-25 |
Knowledge 54.7 ±2.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 45.7% | Epoch AI | 2026-08-27 |
| Humanity's Last Exam | 25.2% | Epoch AI | 2026-11-11 |
| MMLU-Pro (Vals run) | 87.3% | Vals AI | 2026-09-01 |
Frontend 45.9 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 20.6% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,493 | LMArena | 2026-11-09 |
General 58.5 ±3.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,474 | LMArena | 2026-11-09 |
| EQ-Bench Creative Writing v3 | 1,686 | EQ-Bench | 2026-11-11 |
| EQ-Bench Longform Creative Writing | 73.1% | EQ-Bench | 2026-11-11 |
Multimodal 52.1 ±9.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| VPCT | 40.0% | Epoch AI | 2026-11-11 |
| MMMU-Pro (Vals run) | 82.9% | Vals AI | 2026-09-01 |
| GeoBench | 75.0% | Epoch AI | 2026-11-11 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-1 | 40.0% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 7.8% | Epoch AI | A stronger configuration result was used |
| BALROG | 43.0% | Epoch AI | A stronger configuration result was used |
| BFCL v4 | 33.5% | BFCL | A stronger configuration result was used |
| Chess Puzzles | 5.0% | Epoch AI | A stronger configuration result was used |
| DeepResearch Bench | 53.7% | Epoch AI | A stronger configuration result was used |
| Extended NYT Connections | 49.4% | Lech Mazur | A stronger configuration result was used |
| FrontierMath Tier 4 (2025 set) | 4.2% | Epoch AI | A stronger configuration result was used |
| FrontierMath Tiers 1-3 (2025 set) | 20.7% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond | 80.7% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond (Vals run) | 79.5% | Vals AI | A stronger configuration result was used |
| LMArena Text | 1,470 | LMArena | A stronger configuration result was used |
| LMArena WebDev | 1,469 | LMArena | A stronger configuration result was used |
| LiveCodeBench (Vals run) | 75.0% | Vals AI | A stronger configuration result was used |
| METR task suite | 73.0% | Epoch AI | A stronger configuration result was used |
| MMLU-Pro (Vals run) | 85.6% | Vals AI | A stronger configuration result was used |
| MMMU-Pro (Vals run) | 81.1% | Vals AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 48.1% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 59.1% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 58.4% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 57.8% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 54.3% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 52.1% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 51.9% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 51.7% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 59.1% | Epoch AI | A stronger configuration result was used |
Names matched to this model
claude-opus-4-5, claude-opus-4-5-20251101