Model comparison
Claude 3.7 Sonnet vs o3-mini
Claude 3.7 Sonnet is the stronger model overall, scoring 39.5 to 36.7 on the Noometry Index.
Last verified . 40 shared benchmarks.
Summary
- They share 40 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 6 categories and o3-mini in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Claude 3.7 Sonnet leads 50.3 to 33.8.
- The biggest single-benchmark swing is Fiction.LiveBench: 83.3% for Claude 3.7 Sonnet and 50% for o3-mini.
Side by side
| Claude 3.7 Sonnet | o3-mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 39.5 | 36.7 |
| Released | 2025-02-24 | 2024-12-20 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 58 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude 3.7 Sonnet: 40.6 (#136), o3-mini: 40.8 (#132)
| Benchmark | Claude 3.7 Sonnet | o3-mini |
|---|---|---|
| Aider Polyglot | 64.9% | 60.4% |
| GSO | 3.8% | 1.3% |
| LiveBench Coding | 74.5% | 82.7% |
| LMArena Coding | 1361 | 1378 |
| CadEval | 54% | 54% |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| SciCode | — | 39.8% |
| WeirdML | — | 43.7% |
Agentic & Tool Use Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 34.1 (#50), o3-mini: 29.6 (#84)
| Benchmark | Claude 3.7 Sonnet | o3-mini |
|---|---|---|
| Cybench | 20% | 22.5% |
| TheAgentCompany | 30.9% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
Reasoning Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 18.6 (#277), o3-mini: 16.3 (#305)
| Benchmark | Claude 3.7 Sonnet | o3-mini |
|---|---|---|
| ARC-AGI-2 | 0.9% | 3% |
| SimpleBench | 46.4% | 22.8% |
| ARC-AGI-1 | 28.6% | 34.5% |
| LiveBench Reasoning | 87.8% | 89.6% |
| LMArena Hard Prompts | 1333 | 1366 |
| LiveBench Data Analysis | 74% | 70.6% |
| Epoch Capabilities Index | 141.16 | 140.34 |
| ForecastBench | 61.8 | 59.6 |
| LiveBench | 76.1% | 75.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 17% |
| EnigmaEval | 4.2% | — |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 68.8% |
| LMCA | — | 19% |
Math Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 37.5 (#153), o3-mini: 28.1 (#244)
| Benchmark | Claude 3.7 Sonnet | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 76.9% |
| LiveBench Math | 79% | 77.3% |
| LMArena Math | 1337 | 1396 |
| MATH Level 5 | 91.2% | 96.5% |
| FrontierMath (Feb 2025 set) | 4.1% | 12.4% |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| Omni-MATH | 33% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 39.8 (#130), o3-mini: 38.3 (#146)
| Benchmark | Claude 3.7 Sonnet | o3-mini |
|---|---|---|
| GPQA Diamond | 79.7% | 77% |
| Confabulations | 14.7% | 17.9% |
| LMArena Expert | 1321 | 1364 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 15.3% |
| MMLU-Pro | 78.4% | — |
| GPQA (HELM) | 60.8% | — |
Multimodal Not comparable
Claude 3.7 Sonnet: 33.7 (#95), o3-mini: —
| Benchmark | Claude 3.7 Sonnet | o3-mini |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual o3-mini leads
Claude 3.7 Sonnet: 44.1 (#179), o3-mini: 45.7 (#164)
| Benchmark | Claude 3.7 Sonnet | o3-mini |
|---|---|---|
| LMArena Non-English | 1296 | 1319 |
| LMArena Chinese | 1299 | 1379 |
| LMArena French | 1303 | 1334 |
| LMArena German | 1301 | 1303 |
| LMArena Japanese | 1267 | 1286 |
| LMArena Korean | 1249 | 1314 |
| LMArena Russian | 1311 | 1304 |
| LMArena Spanish | 1298 | 1321 |
Instruction Following o3-mini leads
Claude 3.7 Sonnet: 72.9 (#125), o3-mini: 75.1 (#72)
| Benchmark | Claude 3.7 Sonnet | o3-mini |
|---|---|---|
| LiveBench Instruction Following | 81.3% | 84.4% |
| LMArena Instruction Following | 1352 | 1337 |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), o3-mini: 33.8 (#256)
| Benchmark | Claude 3.7 Sonnet | o3-mini |
|---|---|---|
| Fiction.LiveBench | 83.3% | 50% |
| LMArena Longer Query | 1373 | 1343 |
Writing & Preference Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 54.4 (#150), o3-mini: 50.3 (#182)
| Benchmark | Claude 3.7 Sonnet | o3-mini |
|---|---|---|
| LMArena Text | 1314 | 1337 |
| LMArena Creative Writing | 1332 | 1286 |
| Short-Story Creative Writing | 81.1% | 61.7% |
| LMArena Multi-Turn | 1339 | 1320 |
| LiveBench Language | 59.9% | 50.7% |
| EQ-Bench Creative Writing | 1412 | — |
| WildBench | 81.4% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than o3-mini?
Claude 3.7 Sonnet is the stronger model overall, scoring 39.5 to 36.7 on the Noometry Index.
Is Claude 3.7 Sonnet or o3-mini better for coding?
They score almost the same on coding (40.6 vs 40.8); test both on your own repository before choosing.
How many benchmarks do Claude 3.7 Sonnet and o3-mini share?
40 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and o3-mini has 51.