Model comparison
Claude 3.7 Sonnet vs GPT-5 Nano
Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 33.4 on the Noometry Index.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 8 categories and GPT-5 Nano in 2 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in long context, where Claude 3.7 Sonnet leads 50.2 to 31.3.
- The biggest single-benchmark swing is Fiction.LiveBench: 83.3% for Claude 3.7 Sonnet and 44.4% for GPT-5 Nano.
Side by side
| Claude 3.7 Sonnet | GPT-5 Nano | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 39.4 | 33.4 |
| Released | 2025-02-24 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.40 |
| Results tracked | 58 | 48 |
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-5 Nano: 33.3 (#248)
| Benchmark | Claude 3.7 Sonnet | GPT-5 Nano |
|---|---|---|
| SWE-bench Verified (bash only) | 52.8% | 34.8% |
| LMArena Coding | 1361 | 1351 |
| SWE-bench Verified | 61% | — |
| Aider Polyglot | 64.9% | — |
| GSO | 3.8% | — |
| WeirdML | — | 38.1% |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
| ALE-Bench | — | 718.67 |
Agentic & Tool Use Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 33.9 (#46), GPT-5 Nano: 25.6 (#99)
| Benchmark | Claude 3.7 Sonnet | GPT-5 Nano |
|---|---|---|
| Terminal-Bench | — | 21.8% |
| Berkeley Function Calling Leaderboard | — | 51.5% |
| 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-5 Nano: 16.4 (#291)
| Benchmark | Claude 3.7 Sonnet | GPT-5 Nano |
|---|---|---|
| ARC-AGI-2 | 0.9% | 2.6% |
| ARC-AGI-1 | 28.6% | 20.7% |
| LMArena Hard Prompts | 1333 | 1329 |
| Epoch Capabilities Index | 141.16 | 139.39 |
| ForecastBench | 61.8 | 59.1 |
| SimpleBench | 46.4% | — |
| Kagi LLM Benchmark | — | 62.2% |
| Chess Puzzles | — | 27% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 62.7% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 7.9% |
| LiveBench | 76.1% | — |
Math Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 35.7 (#137), GPT-5 Nano: 29.1 (#221)
| Benchmark | Claude 3.7 Sonnet | GPT-5 Nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 81.1% |
| Omni-MATH | 33% | 54.6% |
| LMArena Math | 1336 | 1318 |
| MATH Level 5 | 91.2% | 95.2% |
| FrontierMath (Feb 2025 set) | 4.1% | 8.3% |
| FrontierMath (Tiers 1-3) | — | 20% |
| FrontierMath Tier 4 | — | 2.4% |
| ProofBench | — | 12% |
| LiveBench Math | 79% | — |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 39.7 (#117), GPT-5 Nano: 35.8 (#166)
| Benchmark | Claude 3.7 Sonnet | GPT-5 Nano |
|---|---|---|
| GPQA Diamond | 79.7% | 69.4% |
| MMLU-Pro | 78.4% | 77.8% |
| GPQA (HELM) | 60.8% | 67.9% |
| LMArena Expert | 1321 | 1321 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 11.7% |
| Confabulations | 14.7% | — |
| Vectara Hallucination Rate | — | 10.5% |
Multimodal Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 33.1 (#90), GPT-5 Nano: 30.7 (#102)
| Benchmark | Claude 3.7 Sonnet | GPT-5 Nano |
|---|---|---|
| LMArena Vision | 1169 | 1159 |
| VPCT | 39% | 37.2% |
| GeoBench | 68% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual GPT-5 Nano leads
Claude 3.7 Sonnet: 44.3 (#174), GPT-5 Nano: 45.5 (#167)
| Benchmark | Claude 3.7 Sonnet | GPT-5 Nano |
|---|---|---|
| LMArena Non-English | 1296 | 1313 |
| LMArena Chinese | 1299 | 1355 |
| LMArena German | 1301 | 1329 |
| LMArena Korean | 1249 | 1269 |
| LMArena Russian | 1311 | 1296 |
| LMArena Spanish | 1299 | 1360 |
| LMArena French | 1302 | — |
| LMArena Japanese | 1268 | — |
Instruction Following GPT-5 Nano leads
Claude 3.7 Sonnet: 73.1 (#120), GPT-5 Nano: 75.2 (#72)
| Benchmark | Claude 3.7 Sonnet | GPT-5 Nano |
|---|---|---|
| IFEval | 83.4% | 93.2% |
| LMArena Instruction Following | 1352 | 1306 |
| LiveBench Instruction Following | 81.3% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.2 (#10), GPT-5 Nano: 31.3 (#275)
| Benchmark | Claude 3.7 Sonnet | GPT-5 Nano |
|---|---|---|
| Fiction.LiveBench | 83.3% | 44.4% |
| LMArena Longer Query | 1373 | 1313 |
Writing & Preference Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 54.6 (#145), GPT-5 Nano: 39.4 (#244)
| Benchmark | Claude 3.7 Sonnet | GPT-5 Nano |
|---|---|---|
| LMArena Text | 1314 | 1320 |
| LMArena Creative Writing | 1332 | 1250 |
| EQ-Bench Creative Writing | 1412 | 705 |
| WildBench | 81.4% | 80.6% |
| LMArena Multi-Turn | 1339 | 1311 |
| Short-Story Creative Writing | 81.1% | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than GPT-5 Nano?
Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 33.4 on the Noometry Index.
Is Claude 3.7 Sonnet or GPT-5 Nano better for coding?
Claude 3.7 Sonnet scores higher on coding benchmarks: 41.1 versus 33.3 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and GPT-5 Nano share?
33 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and GPT-5 Nano has 48.