Claude Sonnet 5
| Released | 2026-06-30 |
|---|---|
| Price per 1M | $2.00 in · $10.00 out |
| Overall score | 58.3 · rank 49 |
| Context window | 1,000,000 tokens |
| Provider | Anthropic |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 58.3 | 49 | 42 |
| Overall: Coding | 58.6 | 44 | 28 |
| Overall: Reasoning | 58.1 | 56 | 13 |
| Overall: Agentic work | 58.6 | 50 | 26 |
| Overall: Frontend | 58.5 | 35 | 15 |
| Coding | 58.4 | 40 | 11 |
| Agents | 58.6 | 45 | 9 |
| Reasoning | 58.8 | 58 | 6 |
| Math | 58.7 | 40 | 4 |
| Knowledge | 55.4 | 55 | 3 |
| Frontend | 59.0 | 31 | 2 |
| General | 60.3 | 30 | 5 |
| Multimodal | 55.7 | 43 | 2 |
| Value vs price | +6.4 | 58 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 58.9 ±2.6 | 8 |
| High | 56.2 ±2.8 | 10 |
| Low | 54.2 ±4.6 | 4 |
| Max | 57.9 ±1.2 | 28 |
| Medium | 56.5 ±4.6 | 4 |
| Extra High | 57.1 ±3.0 | 9 |
Evidence
Coding 58.4 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| CursorBench | 34.1% | Epoch AI | 2026-11-11 |
| DeepSWE | 53.9% | Epoch AI | 2026-11-11 |
| FrontierCode | 42.7% | Epoch AI | 2026-11-11 |
| SWE-rebench | 56.8% | SWE-rebench | 2026-07-01 |
| MirrorCode | 63.3% | Epoch AI | 2026-10-21 |
| GSO | 37.3% | Epoch AI | 2026-11-11 |
| IOI | 45.0% | Vals AI | 2026-10-29 |
| SWE-bench Verified (Vals run) | 79.6% | Vals AI | 2026-09-01 |
| SciCode | 54.3% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 82.4% | Vals AI | 2026-09-01 |
| ProgramBench | 0.0% | Vals AI | 2026-11-09 |
Agents 58.6 ±0.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4 | 12.1% | Terminal-Bench | 2026-06-30 |
| SRE Bench | 0.4% | Vals AI | 2026-11-05 |
| Terminal-Bench-Science | 5.7% | Vals AI | 2026-11-09 |
| APEX-Agents | 54.5% | Epoch AI | 2026-11-11 |
| Terminal-Bench 4.0 (Vals run) | 10.6% | Vals AI | 2026-11-09 |
| Terminal-Bench 2.1 (Vals run) | 74.5% | Vals AI | 2026-10-01 |
| Tax Agent Bench | 29.4% | Vals AI | 2026-11-09 |
| SkillsBench | 46.5% | Vals AI | 2026-10-29 |
| Vending-Bench 2 | $6,378 | Epoch AI | 2026-11-11 |
| CyberBench v1.1 | 61.9% | Vals AI | 2026-11-05 |
Reasoning 58.8 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 75.1% | Lech Mazur | 2026-11-10 |
| CritPt | 16.9% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 90.5% | Epoch AI | 2026-07-01 |
| GPQA Diamond (Vals run) | 88.9% | Vals AI | 2026-09-01 |
| Chess Puzzles | 45.0% | Epoch AI | 2026-10-13 |
| SimpleBench | 60.6% | SimpleBench | 2026-07-09 |
| SimpleBench | 60.6% | Epoch AI | 2026-11-11 |
| Mystery Game Puzzles | 35.0% | Epoch AI | 2026-07-28 |
Math 58.7 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 65.6% | Epoch AI | 2026-06-30 |
| FrontierMath Tier 4 | 29.3% | Epoch AI | 2026-06-30 |
| OTIS Mock AIME 2024-2025 | 94.7% | Epoch AI | 2026-07-01 |
| ProofBench v1.1 | 77.0% | Vals AI | 2026-11-09 |
| ProofBench | 77.0% | Epoch AI | 2026-11-11 |
Knowledge 55.4 ±4.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 33.7% | Epoch AI | 2026-08-27 |
| MMLU-Pro (Vals run) | 87.5% | Vals AI | 2026-09-01 |
| Legal Research Bench | 41.8% | Vals AI | 2026-11-09 |
Frontend 59.0 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 81.3% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,539 | LMArena | 2026-11-09 |
General 60.3 ±1.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LLM Debate Benchmark | 1,580 | Lech Mazur | 2026-10-26 |
| EQ-Bench 4 | 1,221 | EQ-Bench | 2026-10-24 |
| EQ-Bench Creative Writing v3 | 1,798 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,461 | LMArena | 2026-11-09 |
| EQ-Bench Longform Creative Writing | 78.3% | EQ-Bench | 2026-11-11 |
Multimodal 55.7 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 83.0% | Vals AI | 2026-09-01 |
| LMArena Vision | 1,261 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| Chess Puzzles | 34.0% | Epoch AI | A stronger configuration result was used |
| CritPt | 15.4% | Epoch AI | A stronger configuration result was used |
| CritPt | 1.1% | Epoch AI | A stronger configuration result was used |
| CritPt | 8.6% | Epoch AI | A stronger configuration result was used |
| CritPt | 4.6% | Epoch AI | A stronger configuration result was used |
| CursorBench | 32.0% | Epoch AI | A stronger configuration result was used |
| CursorBench | 30.8% | Epoch AI | A stronger configuration result was used |
| CursorBench | 28.0% | Epoch AI | A stronger configuration result was used |
| CursorBench | 24.1% | Epoch AI | A stronger configuration result was used |
| DeepSWE | 49.7% | Epoch AI | A stronger configuration result was used |
| DeepSWE | 48.2% | Epoch AI | A stronger configuration result was used |
| DeepSWE | 39.8% | Epoch AI | A stronger configuration result was used |
| DeepSWE | 30.5% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond | 80.3% | Epoch AI | A stronger configuration result was used |
| Mystery Game Puzzles | 16.0% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 80.0% | Epoch AI | A stronger configuration result was used |
| SciCode | 53.6% | Epoch AI | A stronger configuration result was used |
| SciCode | 54.1% | Epoch AI | A stronger configuration result was used |
| SciCode | 51.6% | Epoch AI | A stronger configuration result was used |
| SciCode | 50.1% | Epoch AI | A stronger configuration result was used |
| SimpleQA Verified | 32.9% | Epoch AI | A stronger configuration result was used |
Names matched to this model
claude-sonnet-5