Model comparison
Claude 3.5 Haiku vs Claude 3.7 Sonnet
Claude 3.7 Sonnet is the stronger model overall, scoring 39.5 to 29.2 on the Noometry Index.
Last verified . 41 shared benchmarks.
Summary
- They share 41 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and Claude 3.7 Sonnet in 10 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude 3.7 Sonnet leads 37.5 to 14.7.
- The biggest single-benchmark swing is LiveBench Reasoning: 28.1% for Claude 3.5 Haiku and 87.8% for Claude 3.7 Sonnet.
Side by side
| Claude 3.5 Haiku | Claude 3.7 Sonnet | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 29.2 | 39.5 |
| Released | 2024-10-22 | 2025-02-24 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 49 | 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 Haiku: 32.9 (#265), Claude 3.7 Sonnet: 40.6 (#136)
| Benchmark | Claude 3.5 Haiku | Claude 3.7 Sonnet |
|---|---|---|
| Aider Polyglot | 28% | 64.9% |
| LiveBench Coding | 51.4% | 74.5% |
| LMArena Coding | 1286 | 1361 |
| CadEval | 32% | 54% |
| SWE-bench Verified | — | 61% |
| SWE-bench Verified (bash only) | — | 52.8% |
| SciCode | 27.4% | — |
| GSO | — | 3.8% |
| WeirdML | 30.7% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 59% | — |
Agentic & Tool Use Claude 3.7 Sonnet leads
Claude 3.5 Haiku: 28.0 (#95), Claude 3.7 Sonnet: 34.1 (#50)
| Benchmark | Claude 3.5 Haiku | Claude 3.7 Sonnet |
|---|---|---|
| TheAgentCompany | — | 30.9% |
| Cybench | — | 20% |
| DeepResearch Bench | — | 43.6% |
| OSWorld | — | 35.8% |
| BALROG | 19.3% | — |
| METR Time Horizons | — | 60% |
Reasoning Too close to call
Claude 3.5 Haiku: 17.7 (#290), Claude 3.7 Sonnet: 18.6 (#277)
| Benchmark | Claude 3.5 Haiku | Claude 3.7 Sonnet |
|---|---|---|
| LiveBench Reasoning | 28.1% | 87.8% |
| LMArena Hard Prompts | 1251 | 1333 |
| LiveBench Data Analysis | 48.5% | 74% |
| Epoch Capabilities Index | 127.15 | 141.16 |
| LiveBench | 43.5% | 76.1% |
| ARC-AGI-2 | — | 0.9% |
| SimpleBench | — | 46.4% |
| ARC-AGI-1 | — | 28.6% |
| CritPt | 0% | — |
| EnigmaEval | — | 4.2% |
| DTBench | 56.7% | — |
| ForecastBench | — | 61.8 |
Math Claude 3.7 Sonnet leads
Claude 3.5 Haiku: 14.7 (#300), Claude 3.7 Sonnet: 37.5 (#153)
| Benchmark | Claude 3.5 Haiku | Claude 3.7 Sonnet |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 57.8% |
| Omni-MATH | 22.4% | 33% |
| LiveBench Math | 35.5% | 79% |
| LMArena Math | 1244 | 1337 |
| MATH Level 5 | 46.4% | 91.2% |
| FrontierMath (Feb 2025 set) | 0.3% | 4.1% |
Knowledge Claude 3.7 Sonnet leads
Claude 3.5 Haiku: 18.7 (#281), Claude 3.7 Sonnet: 39.8 (#130)
| Benchmark | Claude 3.5 Haiku | Claude 3.7 Sonnet |
|---|---|---|
| GPQA Diamond | 38.1% | 79.7% |
| MMLU-Pro | 60.5% | 78.4% |
| Confabulations | 36.7% | 14.7% |
| GPQA (HELM) | 36.3% | 60.8% |
| LMArena Expert | 1208 | 1321 |
| Humanity's Last Exam | — | 8% |
| MMLU | 74.3% | — |
Multimodal Claude 3.7 Sonnet leads
Claude 3.5 Haiku: 26.8 (#117), Claude 3.7 Sonnet: 33.7 (#95)
| Benchmark | Claude 3.5 Haiku | Claude 3.7 Sonnet |
|---|---|---|
| LMArena Vision | 1092 | 1169 |
| GeoBench | 34% | 68% |
| VPCT | — | 39% |
| SpatialViz-Bench | — | 33.9% |
Multilingual Claude 3.7 Sonnet leads
Claude 3.5 Haiku: 40.0 (#218), Claude 3.7 Sonnet: 44.1 (#179)
| Benchmark | Claude 3.5 Haiku | Claude 3.7 Sonnet |
|---|---|---|
| LMArena Non-English | 1238 | 1296 |
| LMArena Chinese | 1229 | 1299 |
| LMArena French | 1264 | 1303 |
| LMArena German | 1237 | 1301 |
| LMArena Japanese | 1175 | 1267 |
| LMArena Korean | 1173 | 1249 |
| LMArena Russian | 1253 | 1311 |
| LMArena Spanish | 1261 | 1298 |
Instruction Following Claude 3.7 Sonnet leads
Claude 3.5 Haiku: 62.9 (#234), Claude 3.7 Sonnet: 72.9 (#125)
| Benchmark | Claude 3.5 Haiku | Claude 3.7 Sonnet |
|---|---|---|
| LiveBench Instruction Following | 61.9% | 81.3% |
| IFEval | 79.2% | 83.4% |
| LMArena Instruction Following | 1241 | 1352 |
Long Context Claude 3.7 Sonnet leads
Claude 3.5 Haiku: 38.3 (#200), Claude 3.7 Sonnet: 50.3 (#10)
| Benchmark | Claude 3.5 Haiku | Claude 3.7 Sonnet |
|---|---|---|
| LMArena Longer Query | 1261 | 1373 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference Claude 3.7 Sonnet leads
Claude 3.5 Haiku: 42.7 (#234), Claude 3.7 Sonnet: 54.4 (#150)
| Benchmark | Claude 3.5 Haiku | Claude 3.7 Sonnet |
|---|---|---|
| LMArena Text | 1255 | 1314 |
| LMArena Creative Writing | 1233 | 1332 |
| Short-Story Creative Writing | 73.5% | 81.1% |
| EQ-Bench Creative Writing | 1146 | 1412 |
| WildBench | 76% | 81.4% |
| LMArena Multi-Turn | 1265 | 1339 |
| LiveBench Language | 35.4% | 59.9% |
Frequently asked questions
Is Claude 3.5 Haiku better than Claude 3.7 Sonnet?
Claude 3.7 Sonnet is the stronger model overall, scoring 39.5 to 29.2 on the Noometry Index.
Is Claude 3.5 Haiku or Claude 3.7 Sonnet better for coding?
Claude 3.7 Sonnet scores higher on coding benchmarks: 40.6 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and Claude 3.7 Sonnet share?
41 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Claude 3.7 Sonnet has 58.