Claude Sonnet 4.5
| Released | 2025-09-29 |
|---|---|
| Price per 1M | $3.00 in · $15.00 out |
| Overall score | 52.1 · rank 99 |
| Context window | 200,000 tokens |
| Provider | Anthropic |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 52.1 | 99 | 40 |
| Overall: Coding | 51.3 | 103 | 27 |
| Overall: Reasoning | 51.5 | 100 | 18 |
| Overall: Agentic work | 52.5 | 96 | 25 |
| Overall: Frontend | 48.3 | 107 | 8 |
| Coding | 52.1 | 102 | 4 |
| Agents | 52.8 | 88 | 11 |
| Reasoning | 51.7 | 104 | 10 |
| Math | 51.6 | 98 | 5 |
| Knowledge | 50.7 | 88 | 3 |
| Frontend | 46.0 | 86 | 2 |
| General | 57.2 | 45 | 3 |
| Multimodal | 50.8 | 71 | 2 |
| Value vs price | −1.0 | 132 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 50.8 ±1.0 | 31 |
| High | 52.0 ±6.1 | 2 |
| Low | 51.7 ±7.9 | 1 |
| Non-reasoning | 50.1 ±6.4 | 1 |
| Thinking | 51.4 ±1.4 | 20 |
Evidence
Coding 52.1 ±2.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GSO | 14.7% | Epoch AI | 2026-11-11 |
| SciCode | 45.7% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 73.0% | Vals AI | 2026-09-01 |
| SWE-bench Verified (Epoch run) | 71.3% | Epoch AI | 2026-02-05 |
| SWE-bench Verified (Vals run) | 70.0% | Vals AI | 2026-09-01 |
Agents 52.8 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 2.0 | 46.5% | Epoch AI | 2025-09-29 |
| Remote Labor Index | 2.1% | Epoch AI | 2026-11-11 |
| METR task suite | 67.4% | Epoch AI | 2026-11-11 |
| tau2-bench Banking Knowledge | 25.3% | tau2-bench | 2026-02-24 |
| BFCL v4 | 73.2% | BFCL | 2026-04-12 |
| OSWorld-Verified | 62.9% | OSWorld-Verified | 2025-10-31 |
| tau2-bench Airline | 72.0% | tau2-bench | 2026-02-24 |
| DeepResearch Bench | 52.6% | Epoch AI | 2026-11-11 |
| OSWorld (v1) | 62.9% | Epoch AI | 2026-11-11 |
| Vending-Bench 2 | $3,839 | Epoch AI | 2026-11-11 |
| tau2-bench Telecom | 84.9% | tau2-bench | 2026-02-24 |
| tau2-bench Retail | 72.4% | tau2-bench | 2026-02-24 |
Reasoning 51.7 ±1.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 13.6% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 13.6% | ARC Prize | 2026-11-11 |
| Extended NYT Connections | 37.3% | Lech Mazur | 2026-11-10 |
| CritPt | 1.1% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 63.7% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 63.7% | Epoch AI | 2026-11-11 |
| EnigmaEval | 6.0% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 82.3% | Epoch AI | 2025-10-28 |
| GPQA Diamond (Vals run) | 81.6% | Vals AI | 2026-09-01 |
| Kagi Reasoning Benchmark | 57.9% | Kagi | 2026-11-11 |
| Chess Puzzles | 10.0% | Epoch AI | 2026-10-13 |
| SimpleBench | 54.3% | SimpleBench | 2026-11-11 |
| SimpleBench | 54.3% | Epoch AI | 2026-11-11 |
| Mystery Game Puzzles | 17.0% | Epoch AI | 2026-07-25 |
Math 51.6 ±1.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 23.9% | Epoch AI | 2026-06-11 |
| MATH Level 5 | 97.7% | Epoch AI | 2025-10-21 |
| FrontierMath Tier 4 | 2.4% | Epoch AI | 2026-06-11 |
| ProofBench | 19.0% | Epoch AI | 2026-11-11 |
| OTIS Mock AIME 2024-2025 | 77.8% | Epoch AI | 2025-10-28 |
| FrontierMath Tiers 1-3 (2025 set) | 15.2% | Epoch AI | 2025-11-16 |
| FrontierMath Tier 4 (2025 set) | 4.2% | Epoch AI | 2025-10-22 |
Knowledge 50.7 ±3.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 30.7% | Epoch AI | 2026-08-27 |
| Humanity's Last Exam | 13.7% | Epoch AI | 2026-11-11 |
| MMLU-Pro (Vals run) | 87.4% | Vals AI | 2026-09-01 |
Frontend 46.0 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 22.6% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,393 | LMArena | 2026-11-09 |
General 57.2 ±3.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,456 | LMArena | 2026-11-09 |
| EQ-Bench Creative Writing v3 | 1,677 | EQ-Bench | 2026-11-11 |
| EQ-Bench Longform Creative Writing | 71.4% | EQ-Bench | 2026-11-11 |
Multimodal 50.8 ±2.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 79.3% | Vals AI | 2026-09-01 |
| VPCT | 39.8% | Epoch AI | 2026-11-11 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-1 | 25.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 25.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 | 3.8% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 3.8% | ARC Prize | A stronger configuration result was used |
| BFCL v4 | 24.9% | BFCL | A stronger configuration result was used |
| Chess Puzzles | 6.0% | Epoch AI | A stronger configuration result was used |
| DeepResearch Bench | 47.5% | Epoch AI | A stronger configuration result was used |
| Extended NYT Connections | 35.8% | Lech Mazur | A stronger configuration result was used |
| FrontierMath Tier 4 (2025 set) | 2.1% | Epoch AI | A stronger configuration result was used |
| FrontierMath Tiers 1-3 (2025 set) | 9.3% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond | 73.7% | Epoch AI | A stronger configuration result was used |
| LMArena Text | 1,455 | LMArena | A stronger configuration result was used |
| LMArena WebDev | 1,385 | LMArena | A stronger configuration result was used |
| OSWorld (v1) | 58.1% | Epoch AI | A stronger configuration result was used |
| OSWorld (v1) | 42.9% | Epoch AI | A stronger configuration result was used |
| OSWorld-Verified | 42.9% | OSWorld-Verified | A stronger configuration result was used |
| OSWorld-Verified | 58.1% | OSWorld-Verified | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 35.6% | Epoch AI | A stronger configuration result was used |
| SimpleBench | 54.3% | Epoch AI | A stronger configuration result was used |
| SimpleQA Verified | 23.7% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 43.2% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 42.8% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 42.7% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 42.7% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 42.6% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 42.5% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 40.1% | Epoch AI | A stronger configuration result was used |
| VPCT | 38.0% | Epoch AI | A stronger configuration result was used |
Names matched to this model
claude-sonnet-4-5, claude-sonnet-4-5-20250929