Claude 3.5 Sonnet
| Released | 2024-06-20 |
|---|---|
| Price per 1M | Not listed |
| Overall score | 39.2 · rank 197 |
| Provider | Anthropic |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 39.2 | 197 | 11 |
| Overall: Coding | 37.5 | 201 | 3 |
| Overall: Reasoning | 39.4 | 196 | 6 |
| Overall: Agentic work | 36.8 | 207 | 3 |
| Overall: Frontend | 42.4 | 162 | 2 |
| Agents | 35.7 | 171 | 1 |
| Reasoning | 41.0 | 183 | 2 |
| Math | 37.4 | 172 | 4 |
| General | 43.7 | 145 | 2 |
| Multimodal | 42.4 | 101 | 2 |
Evidence
Agents 35.7 ±2.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| METR 50% Time Horizon | $11 | METR | 2026-11-11 |
| METR task suite | 40.2% | Epoch AI | 2026-11-11 |
Reasoning 41.0 ±5.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 54.0% | Epoch AI | 2025-01-27 |
| SimpleBench | 41.4% | SimpleBench | 2026-11-11 |
| SimpleBench | 27.5% | Epoch AI | 2026-11-11 |
Math 37.4 ±2.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MATH Level 5 | 51.7% | Epoch AI | 2025-01-27 |
| FrontierMath Tiers 1-3 (2025 set) | 1.0% | Epoch AI | 2025-03-07 |
| FrontierMath Tier 4 (2025 set) | 0.0% | Epoch AI | 2025-07-01 |
| OTIS Mock AIME 2024-2025 | 6.5% | Epoch AI | 2025-02-25 |
General 43.7 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,343 | LMArena | 2026-11-09 |
| EQ-Bench Longform Creative Writing | 58.4% | EQ-Bench | 2026-11-11 |
Multimodal 42.4 ±3.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Vision | 1,146 | LMArena | 2026-11-09 |
| VPCT | 33.0% | Epoch AI | 2026-11-11 |
Names matched to this model
claude-sonnet-3-5, claude-sonnet-3-5-20240620