Model comparison
Claude 3.7 Sonnet vs GPT-4.1 mini
Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 33.5 on the Noometry Index.
Last verified . 35 shared benchmarks.
Summary
- They share 35 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 7 categories and GPT-4.1 mini in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Claude 3.7 Sonnet leads 50.2 to 31.8.
- The biggest single-benchmark swing is Fiction.LiveBench: 83.3% for Claude 3.7 Sonnet and 44.4% for GPT-4.1 mini.
Side by side
| Claude 3.7 Sonnet | GPT-4.1 mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 39.4 | 33.5 |
| Released | 2025-02-24 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $1.60 |
| Results tracked | 58 | 47 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 41.1 (#120), GPT-4.1 mini: 30.4 (#286)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 mini |
|---|---|---|
| SWE-bench Verified (bash only) | 52.8% | 23.9% |
| Aider Polyglot | 64.9% | 32.4% |
| LMArena Coding | 1361 | 1367 |
| CadEval | 54% | 16% |
| SWE-bench Verified | 61% | — |
| SciCode | — | 40.4% |
| GSO | 3.8% | — |
| WeirdML | — | 37.6% |
| BigCodeBench Instruct | — | 48.9% |
| LiveBench Coding | 74.5% | — |
Agentic & Tool Use Too close to call
Claude 3.7 Sonnet: 33.9 (#46), GPT-4.1 mini: 33.0 (#52)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 50.5% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
Reasoning Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 18.7 (#252), GPT-4.1 mini: 10.9 (#335)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 mini |
|---|---|---|
| ARC-AGI-2 | 0.9% | 0% |
| ARC-AGI-1 | 28.6% | 3.5% |
| LMArena Hard Prompts | 1333 | 1349 |
| Epoch Capabilities Index | 141.16 | 135.01 |
| SimpleBench | 46.4% | — |
| Kagi LLM Benchmark | — | 48.6% |
| CritPt | — | 0% |
| Chess Puzzles | — | 7% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 68.8% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 21.1% |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |
Math Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 35.7 (#137), GPT-4.1 mini: 23.1 (#264)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 44.7% |
| Omni-MATH | 33% | 49.1% |
| LMArena Math | 1336 | 1343 |
| MATH Level 5 | 91.2% | 87.3% |
| FrontierMath (Feb 2025 set) | 4.1% | 4.5% |
| FrontierMath (Tiers 1-3) | — | 6.7% |
| LiveBench Math | 79% | — |
Knowledge Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 39.7 (#117), GPT-4.1 mini: 34.7 (#183)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 mini |
|---|---|---|
| GPQA Diamond | 79.7% | 65.8% |
| MMLU-Pro | 78.4% | 78.3% |
| GPQA (HELM) | 60.8% | 61.4% |
| LMArena Expert | 1321 | 1338 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 12.7% |
| Confabulations | 14.7% | — |
Multimodal GPT-4.1 mini leads
Claude 3.7 Sonnet: 33.1 (#90), GPT-4.1 mini: 35.2 (#77)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 mini |
|---|---|---|
| LMArena Vision | 1169 | 1181 |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual GPT-4.1 mini leads
Claude 3.7 Sonnet: 44.3 (#174), GPT-4.1 mini: 45.9 (#161)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 mini |
|---|---|---|
| LMArena Non-English | 1296 | 1318 |
| LMArena Chinese | 1299 | 1329 |
| LMArena French | 1302 | 1357 |
| LMArena German | 1301 | 1349 |
| LMArena Japanese | 1268 | 1291 |
| LMArena Korean | 1249 | 1298 |
| LMArena Russian | 1311 | 1324 |
| LMArena Spanish | 1299 | 1319 |
Instruction Following Too close to call
Claude 3.7 Sonnet: 73.1 (#120), GPT-4.1 mini: 73.9 (#113)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 mini |
|---|---|---|
| IFEval | 83.4% | 90.4% |
| LMArena Instruction Following | 1352 | 1332 |
| LiveBench Instruction Following | 81.3% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.2 (#10), GPT-4.1 mini: 31.8 (#270)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 mini |
|---|---|---|
| Fiction.LiveBench | 83.3% | 44.4% |
| LMArena Longer Query | 1373 | 1344 |
Writing & Preference Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 54.6 (#145), GPT-4.1 mini: 48.8 (#193)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 mini |
|---|---|---|
| LMArena Text | 1314 | 1341 |
| LMArena Creative Writing | 1332 | 1300 |
| EQ-Bench Creative Writing | 1412 | 1147 |
| WildBench | 81.4% | 83.8% |
| LMArena Multi-Turn | 1339 | 1354 |
| Short-Story Creative Writing | 81.1% | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than GPT-4.1 mini?
Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 33.5 on the Noometry Index.
Is Claude 3.7 Sonnet or GPT-4.1 mini better for coding?
Claude 3.7 Sonnet scores higher on coding benchmarks: 41.1 versus 30.4 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and GPT-4.1 mini share?
35 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and GPT-4.1 mini has 47.