Model comparison
Claude 3.5 Sonnet vs Claude 3.7 Sonnet
Claude 3.7 Sonnet is the stronger model overall, scoring 39.5 to 34.6 on the Noometry Index.
Last verified . 50 shared benchmarks.
Summary
- They share 50 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 1 category and Claude 3.7 Sonnet in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude 3.7 Sonnet leads 37.5 to 19.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 57.8% for Claude 3.7 Sonnet.
Side by side
| Claude 3.5 Sonnet | Claude 3.7 Sonnet | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 34.6 | 39.5 |
| Released | 2024-06-20 | 2025-02-24 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 60 | 58 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.7 Sonnet leads
Claude 3.5 Sonnet: 39.0 (#165), Claude 3.7 Sonnet: 40.6 (#136)
| Benchmark | Claude 3.5 Sonnet | Claude 3.7 Sonnet |
|---|---|---|
| Aider Polyglot | 51.6% | 64.9% |
| GSO | 4.6% | 3.8% |
| LiveBench Coding | 67.1% | 74.5% |
| LMArena Coding | 1342 | 1361 |
| CadEval | 48% | 54% |
| SWE-bench Verified | — | 61% |
| SWE-bench Verified (bash only) | — | 52.8% |
| WeirdML | 40% | — |
| BigCodeBench Instruct | 46.8% | — |
| BigCodeBench Complete | 58.6% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Claude 3.7 Sonnet leads
Claude 3.5 Sonnet: 32.3 (#67), Claude 3.7 Sonnet: 34.1 (#50)
| Benchmark | Claude 3.5 Sonnet | Claude 3.7 Sonnet |
|---|---|---|
| TheAgentCompany | 24% | 30.9% |
| Cybench | 17.5% | 20% |
| METR Time Horizons | 45.2% | 60% |
| DeepResearch Bench | — | 43.6% |
| OSWorld | — | 35.8% |
| BALROG | 32.6% | — |
Reasoning Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 23.1 (#183), Claude 3.7 Sonnet: 18.6 (#277)
| Benchmark | Claude 3.5 Sonnet | Claude 3.7 Sonnet |
|---|---|---|
| SimpleBench | 41.4% | 46.4% |
| EnigmaEval | 0.9% | 4.2% |
| LiveBench Reasoning | 56.7% | 87.8% |
| LMArena Hard Prompts | 1305 | 1333 |
| LiveBench Data Analysis | 55% | 74% |
| Epoch Capabilities Index | 133.55 | 141.16 |
| ForecastBench | 60.7 | 61.8 |
| LiveBench | 59% | 76.1% |
| ARC-AGI-2 | — | 0.9% |
| ARC-AGI-1 | — | 28.6% |
| DTBench | 67.8% | — |
Math Claude 3.7 Sonnet leads
Claude 3.5 Sonnet: 19.2 (#288), Claude 3.7 Sonnet: 37.5 (#153)
| Benchmark | Claude 3.5 Sonnet | Claude 3.7 Sonnet |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 57.8% |
| Omni-MATH | 27.6% | 33% |
| LiveBench Math | 52.3% | 79% |
| LMArena Math | 1307 | 1337 |
| MATH Level 5 | 56.9% | 91.2% |
| FrontierMath (Feb 2025 set) | 2.1% | 4.1% |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude 3.7 Sonnet leads
Claude 3.5 Sonnet: 28.6 (#245), Claude 3.7 Sonnet: 39.8 (#130)
| Benchmark | Claude 3.5 Sonnet | Claude 3.7 Sonnet |
|---|---|---|
| GPQA Diamond | 55.3% | 79.7% |
| Humanity's Last Exam | 4.1% | 8% |
| MMLU-Pro | 77.7% | 78.4% |
| Confabulations | 19.9% | 14.7% |
| GPQA (HELM) | 56.5% | 60.8% |
| LMArena Expert | 1265 | 1321 |
| MMLU | 87.3% | — |
Multimodal Claude 3.7 Sonnet leads
Claude 3.5 Sonnet: 26.5 (#120), Claude 3.7 Sonnet: 33.7 (#95)
| Benchmark | Claude 3.5 Sonnet | Claude 3.7 Sonnet |
|---|---|---|
| LMArena Vision | 1125 | 1169 |
| GeoBench | 62% | 68% |
| VPCT | 33% | 39% |
| Video-MME | 60% | — |
| SpatialViz-Bench | — | 33.9% |
Multilingual Too close to call
Claude 3.5 Sonnet: 43.2 (#185), Claude 3.7 Sonnet: 44.1 (#179)
| Benchmark | Claude 3.5 Sonnet | Claude 3.7 Sonnet |
|---|---|---|
| LMArena Non-English | 1283 | 1296 |
| LMArena Chinese | 1272 | 1299 |
| LMArena French | 1305 | 1303 |
| LMArena German | 1297 | 1301 |
| LMArena Japanese | 1234 | 1267 |
| LMArena Korean | 1200 | 1249 |
| LMArena Russian | 1306 | 1311 |
| LMArena Spanish | 1290 | 1298 |
Instruction Following Claude 3.7 Sonnet leads
Claude 3.5 Sonnet: 68.8 (#182), Claude 3.7 Sonnet: 72.9 (#125)
| Benchmark | Claude 3.5 Sonnet | Claude 3.7 Sonnet |
|---|---|---|
| LiveBench Instruction Following | 69.3% | 81.3% |
| IFEval | 85.5% | 83.4% |
| LMArena Instruction Following | 1297 | 1352 |
Long Context Claude 3.7 Sonnet leads
Claude 3.5 Sonnet: 39.9 (#167), Claude 3.7 Sonnet: 50.3 (#10)
| Benchmark | Claude 3.5 Sonnet | Claude 3.7 Sonnet |
|---|---|---|
| LMArena Longer Query | 1311 | 1373 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference Claude 3.7 Sonnet leads
Claude 3.5 Sonnet: 52.9 (#164), Claude 3.7 Sonnet: 54.4 (#150)
| Benchmark | Claude 3.5 Sonnet | Claude 3.7 Sonnet |
|---|---|---|
| LMArena Text | 1298 | 1314 |
| LMArena Creative Writing | 1292 | 1332 |
| Short-Story Creative Writing | 80.3% | 81.1% |
| EQ-Bench Creative Writing | 1451 | 1412 |
| WildBench | 79.2% | 81.4% |
| LMArena Multi-Turn | 1326 | 1339 |
| LiveBench Language | 53.8% | 59.9% |
Frequently asked questions
Is Claude 3.5 Sonnet better than Claude 3.7 Sonnet?
Claude 3.7 Sonnet is the stronger model overall, scoring 39.5 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or Claude 3.7 Sonnet better for coding?
Claude 3.7 Sonnet scores higher on coding benchmarks: 40.6 versus 39.0 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Claude 3.7 Sonnet share?
50 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Claude 3.7 Sonnet has 58.