Model comparison
Claude 3.7 Sonnet vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 to 39.4 on the Noometry Index.
Last verified . 44 shared benchmarks.
Summary
- They share 44 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 3 categories and o4-mini in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where o4-mini leads 39.5 to 33.1.
- The biggest single-benchmark swing is Omni-MATH: 33% for Claude 3.7 Sonnet and 72% for o4-mini.
Side by side
| Claude 3.7 Sonnet | o4-mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 39.4 | 41.6 |
| Released | 2025-02-24 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 58 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude 3.7 Sonnet: 41.1 (#120), o4-mini: 41.6 (#110)
| Benchmark | Claude 3.7 Sonnet | o4-mini |
|---|---|---|
| SWE-bench Verified (bash only) | 52.8% | 45% |
| Aider Polyglot | 64.9% | 72% |
| GSO | 3.8% | 3.6% |
| LMArena Coding | 1361 | 1369 |
| CadEval | 54% | 62% |
| SWE-bench Verified | 61% | — |
| WeirdML | — | 52.6% |
| LiveBench Coding | 74.5% | — |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
Agentic & Tool Use Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 33.9 (#46), o4-mini: 32.3 (#57)
| Benchmark | Claude 3.7 Sonnet | o4-mini |
|---|---|---|
| METR Time Horizons | 60% | 63.9% |
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
Reasoning o4-mini leads
Claude 3.7 Sonnet: 18.7 (#252), o4-mini: 24.6 (#143)
| Benchmark | Claude 3.7 Sonnet | o4-mini |
|---|---|---|
| ARC-AGI-2 | 0.9% | 6.1% |
| SimpleBench | 46.4% | 38.7% |
| ARC-AGI-1 | 28.6% | 58.7% |
| EnigmaEval | 4.2% | 9.2% |
| LMArena Hard Prompts | 1333 | 1351 |
| Epoch Capabilities Index | 141.16 | 145.63 |
| ForecastBench | 61.8 | 61.8 |
| Kagi LLM Benchmark | — | 67.6% |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 26% |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 77.6% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 26.5% |
| LiveBench | 76.1% | — |
Math o4-mini leads
Claude 3.7 Sonnet: 35.7 (#137), o4-mini: 40.2 (#79)
| Benchmark | Claude 3.7 Sonnet | o4-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 81.7% |
| Omni-MATH | 33% | 72% |
| LMArena Math | 1336 | 1390 |
| MATH Level 5 | 91.2% | 97.8% |
| FrontierMath (Feb 2025 set) | 4.1% | 24.8% |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| LiveBench Math | 79% | — |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
Claude 3.7 Sonnet: 39.7 (#117), o4-mini: 43.5 (#83)
| Benchmark | Claude 3.7 Sonnet | o4-mini |
|---|---|---|
| GPQA Diamond | 79.7% | 79.6% |
| Humanity's Last Exam | 8% | 18.1% |
| MMLU-Pro | 78.4% | 82% |
| Confabulations | 14.7% | 15.8% |
| GPQA (HELM) | 60.8% | 73.5% |
| LMArena Expert | 1321 | 1344 |
| SimpleQA Verified | — | 19.6% |
| Vectara Hallucination Rate | — | 18.6% |
Multimodal o4-mini leads
Claude 3.7 Sonnet: 33.1 (#90), o4-mini: 39.5 (#46)
| Benchmark | Claude 3.7 Sonnet | o4-mini |
|---|---|---|
| LMArena Vision | 1169 | 1194 |
| GeoBench | 68% | 64% |
| VPCT | 39% | 57.5% |
| SpatialViz-Bench | 33.9% | — |
Multilingual o4-mini leads
Claude 3.7 Sonnet: 44.3 (#174), o4-mini: 47.2 (#149)
| Benchmark | Claude 3.7 Sonnet | o4-mini |
|---|---|---|
| LMArena Non-English | 1296 | 1336 |
| LMArena Chinese | 1299 | 1355 |
| LMArena French | 1302 | 1362 |
| LMArena German | 1301 | 1336 |
| LMArena Japanese | 1268 | 1308 |
| LMArena Korean | 1249 | 1313 |
| LMArena Russian | 1311 | 1334 |
| LMArena Spanish | 1299 | 1346 |
Instruction Following o4-mini leads
Claude 3.7 Sonnet: 73.1 (#120), o4-mini: 75.4 (#63)
| Benchmark | Claude 3.7 Sonnet | o4-mini |
|---|---|---|
| IFEval | 83.4% | 92.8% |
| LMArena Instruction Following | 1352 | 1321 |
| LiveBench Instruction Following | 81.3% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.2 (#10), o4-mini: 45.5 (#31)
| Benchmark | Claude 3.7 Sonnet | o4-mini |
|---|---|---|
| Fiction.LiveBench | 83.3% | 77.8% |
| LMArena Longer Query | 1373 | 1315 |
Writing & Preference Too close to call
Claude 3.7 Sonnet: 54.6 (#145), o4-mini: 54.2 (#148)
| Benchmark | Claude 3.7 Sonnet | o4-mini |
|---|---|---|
| LMArena Text | 1314 | 1353 |
| LMArena Creative Writing | 1332 | 1294 |
| Short-Story Creative Writing | 81.1% | 75% |
| WildBench | 81.4% | 85.4% |
| LMArena Multi-Turn | 1339 | 1350 |
| EQ-Bench Creative Writing | 1412 | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 39.4 on the Noometry Index.
Is Claude 3.7 Sonnet or o4-mini better for coding?
They score almost the same on coding (41.1 vs 41.6); test both on your own repository before choosing.
How many benchmarks do Claude 3.7 Sonnet and o4-mini share?
44 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and o4-mini has 60.