Model comparison
Claude 3.7 Sonnet vs GPT-4.1
Claude 3.7 Sonnet is the stronger model overall, scoring 39.5 to 35.9 on the Noometry Index.
Last verified . 41 shared benchmarks.
Summary
- They share 41 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 6 categories and GPT-4.1 in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude 3.7 Sonnet leads 37.5 to 22.3.
- The biggest single-benchmark swing is ARC-AGI-1: 28.6% for Claude 3.7 Sonnet and 5.5% for GPT-4.1.
Side by side
| Claude 3.7 Sonnet | GPT-4.1 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 39.5 | 35.9 |
| Released | 2025-02-24 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 33K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $8 |
| Results tracked | 58 | 52 |
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: 40.6 (#136), GPT-4.1: 34.4 (#238)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 |
|---|---|---|
| SWE-bench Verified | 61% | 48.5% |
| SWE-bench Verified (bash only) | 52.8% | 39.6% |
| Aider Polyglot | 64.9% | 52.4% |
| LMArena Coding | 1361 | 1391 |
| CadEval | 54% | 42% |
| GSO | 3.8% | — |
| WeirdML | — | 39% |
| LiveBench Coding | 74.5% | — |
| ALE-Bench | — | 558.1 |
Agentic & Tool Use Too close to call
Claude 3.7 Sonnet: 34.1 (#50), GPT-4.1: 34.7 (#43)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 54% |
| 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: 18.6 (#277), GPT-4.1: 11.7 (#339)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 |
|---|---|---|
| ARC-AGI-2 | 0.9% | 0.4% |
| SimpleBench | 46.4% | 27% |
| ARC-AGI-1 | 28.6% | 5.5% |
| EnigmaEval | 4.2% | 2.2% |
| LMArena Hard Prompts | 1333 | 1384 |
| Epoch Capabilities Index | 141.16 | 136.78 |
| ForecastBench | 61.8 | 61.5 |
| Kagi LLM Benchmark | — | 52.3% |
| Chess Puzzles | — | 6% |
| LiveBench Reasoning | 87.8% | — |
| DTBench | — | 68.3% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 25.6% |
| LiveBench | 76.1% | — |
Math Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 37.5 (#153), GPT-4.1: 22.3 (#280)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 38.3% |
| Omni-MATH | 33% | 47.1% |
| LMArena Math | 1337 | 1370 |
| MATH Level 5 | 91.2% | 83% |
| FrontierMath (Feb 2025 set) | 4.1% | 5.5% |
| FrontierMath (Tiers 1-3) | — | 6% |
| LiveBench Math | 79% | — |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 39.8 (#130), GPT-4.1: 37.1 (#160)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 |
|---|---|---|
| GPQA Diamond | 79.7% | 66.9% |
| Humanity's Last Exam | 8% | 5.4% |
| MMLU-Pro | 78.4% | 81.1% |
| GPQA (HELM) | 60.8% | 65.9% |
| LMArena Expert | 1321 | 1364 |
| SimpleQA Verified | — | 31.1% |
| Confabulations | 14.7% | — |
| Vectara Hallucination Rate | — | 5.6% |
Multimodal GPT-4.1 leads
Claude 3.7 Sonnet: 33.7 (#95), GPT-4.1: 38.2 (#67)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 |
|---|---|---|
| LMArena Vision | 1169 | 1211 |
| GeoBench | 68% | 72% |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual GPT-4.1 leads
Claude 3.7 Sonnet: 44.1 (#179), GPT-4.1: 49.4 (#133)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 1296 | 1370 |
| LMArena Chinese | 1299 | 1382 |
| LMArena French | 1303 | 1382 |
| LMArena German | 1301 | 1381 |
| LMArena Japanese | 1267 | 1319 |
| LMArena Korean | 1249 | 1339 |
| LMArena Russian | 1311 | 1377 |
| LMArena Spanish | 1298 | 1376 |
Instruction Following Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 72.9 (#125), GPT-4.1: 71.3 (#153)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 |
|---|---|---|
| IFEval | 83.4% | 83.8% |
| LMArena Instruction Following | 1352 | 1367 |
| LiveBench Instruction Following | 81.3% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), GPT-4.1: 40.0 (#163)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 |
|---|---|---|
| Fiction.LiveBench | 83.3% | 63.9% |
| LMArena Longer Query | 1373 | 1385 |
Writing & Preference GPT-4.1 leads
Claude 3.7 Sonnet: 54.4 (#150), GPT-4.1: 57.6 (#125)
| Benchmark | Claude 3.7 Sonnet | GPT-4.1 |
|---|---|---|
| LMArena Text | 1314 | 1383 |
| LMArena Creative Writing | 1332 | 1363 |
| EQ-Bench Creative Writing | 1412 | 1420 |
| WildBench | 81.4% | 85.4% |
| LMArena Multi-Turn | 1339 | 1398 |
| Short-Story Creative Writing | 81.1% | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than GPT-4.1?
Claude 3.7 Sonnet is the stronger model overall, scoring 39.5 to 35.9 on the Noometry Index.
Is Claude 3.7 Sonnet or GPT-4.1 better for coding?
Claude 3.7 Sonnet scores higher on coding benchmarks: 40.6 versus 34.4 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and GPT-4.1 share?
41 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and GPT-4.1 has 52.