Claude Opus 4.5 Thinking
| Released | 2025-11-24 |
|---|---|
| Price per 1M | $5.00 in · $25.00 out |
| Overall score | 54.1 · rank 209 |
| Context window | 200,000 tokens |
| Provider | Anthropic |
| Weights | Proprietary |
| Configuration | Thinking |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 54.1 | 209 | 19 |
| Overall: Coding | 53.5 | 212 | 12 |
| Overall: Reasoning | 54.6 | 198 | 11 |
| Overall: Agentic work | 54.7 | 209 | 11 |
| Overall: Frontend | 49.3 | 227 | 5 |
| Coding | 54.8 | 182 | 2 |
| Agents | 54.4 | 154 | 3 |
| Reasoning | 55.8 | 193 | 6 |
| Math | 52.8 | 150 | 3 |
| Knowledge | 55.2 | 74 | 2 |
| Frontend | 45.8 | 146 | 1 |
| Multimodal | 53.5 | 89 | 2 |
| Value vs price | −2.6 | 279 |
Evidence
Coding 54.8 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SWE-bench Verified (Vals run) | 76.4% | Vals AI | 2026-09-01 |
| LiveCodeBench (Vals run) | 83.7% | Vals AI | 2026-09-01 |
Agents 54.4 ±4.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 2.0 | 59.1% | Epoch AI | 2025-12-17 |
| METR task suite | 75.0% | Epoch AI | 2026-11-11 |
| BALROG | 43.0% | Epoch AI | 2026-11-11 |
Reasoning 55.8 ±2.0
| 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 |
| GPQA Diamond | 86.1% | Epoch AI | 2025-11-24 |
| GPQA Diamond (Vals run) | 85.9% | Vals AI | 2026-09-01 |
| Chess Puzzles | 14.0% | Epoch AI | 2026-10-13 |
| Mystery Game Puzzles | 22.0% | Epoch AI | 2026-07-25 |
Math 52.8 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.1% | Epoch AI | 2025-11-24 |
| FrontierMath Tier 4 | 4.9% | Epoch AI | 2026-06-11 |
| FrontierMath Tiers 1-3 | 34.4% | Epoch AI | 2026-06-11 |
| 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 55.2 ±2.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 45.7% | Epoch AI | 2026-08-27 |
| MMLU-Pro (Vals run) | 87.3% | Vals AI | 2026-09-01 |
Frontend 45.8 ±0.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 20.6% | Vals AI | 2026-11-09 |
Multimodal 53.5 ±2.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 82.9% | Vals AI | 2026-09-01 |
| VPCT | 40.0% | Epoch AI | 2026-11-11 |
Names matched to this model
claude-opus-4-5-20251101-thinking