Model comparison
Claude 3.7 Sonnet vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 61.8 to 39.5 on the Noometry Index.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 1 category and GPT-6 Sol in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 74.0 to 18.6.
- The biggest single-benchmark swing is ARC-AGI-2: 0.9% for Claude 3.7 Sonnet and 89.6% for GPT-6 Sol.
Side by side
| Claude 3.7 Sonnet | GPT-6 Sol | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 39.5 | 61.8 |
| Released | 2025-02-24 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $10 |
| Results tracked | 58 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
Claude 3.7 Sonnet: 40.6 (#136), GPT-6 Sol: 60.1 (#11)
| Benchmark | Claude 3.7 Sonnet | GPT-6 Sol |
|---|---|---|
| LMArena Coding | 1361 | 1447 |
| SWE-bench Verified | 61% | — |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| LMArena WebDev | — | 1688 |
| SciCode | — | 57.6% |
| GSO | 3.8% | — |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
| ALE-Bench | — | 2,462 |
Agentic & Tool Use GPT-6 Sol leads
Claude 3.7 Sonnet: 34.1 (#50), GPT-6 Sol: 37.2 (#36)
| Benchmark | Claude 3.7 Sonnet | GPT-6 Sol |
|---|---|---|
| APEX-Agents | — | 54.3% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| GDP.pdf | — | 26.4% |
| METR Time Horizons | 60% | — |
| Vending-Bench 2 | — | 14,428 |
Reasoning GPT-6 Sol leads
Claude 3.7 Sonnet: 18.6 (#277), GPT-6 Sol: 74.0 (#9)
| Benchmark | Claude 3.7 Sonnet | GPT-6 Sol |
|---|---|---|
| ARC-AGI-2 | 0.9% | 89.6% |
| ARC-AGI-1 | 28.6% | 95.5% |
| LMArena Hard Prompts | 1333 | 1418 |
| Epoch Capabilities Index | 141.16 | 162.72 |
| SimpleBench | 46.4% | — |
| NYT Connections (extended) | — | 90.1% |
| CritPt | — | 30.9% |
| EnigmaEval | 4.2% | — |
| EBR-Bench | — | 53.3% |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 56% |
| DTBench | — | 97.3% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 59.1% |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |
Math GPT-6 Sol leads
Claude 3.7 Sonnet: 37.5 (#153), GPT-6 Sol: 87.2 (#7)
| Benchmark | Claude 3.7 Sonnet | GPT-6 Sol |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 100% |
| LMArena Math | 1337 | 1402 |
| FrontierMath (Tiers 1-3) | — | 89.8% |
| FrontierMath Tier 4 | — | 90% |
| ProofBench | — | 83% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge GPT-6 Sol leads
Claude 3.7 Sonnet: 39.8 (#130), GPT-6 Sol: 64.8 (#15)
| Benchmark | Claude 3.7 Sonnet | GPT-6 Sol |
|---|---|---|
| GPQA Diamond | 79.7% | 94.3% |
| LMArena Expert | 1321 | 1439 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 60.7% |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| Vectara Hallucination Rate | — | 6.5% |
| GPQA (HELM) | 60.8% | — |
Multimodal GPT-6 Sol leads
Claude 3.7 Sonnet: 33.7 (#95), GPT-6 Sol: 47.6 (#10)
| Benchmark | Claude 3.7 Sonnet | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 1169 | 1245 |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| Blueprint-Bench 2 | — | 36.9% |
| Furniture Assembly | — | 58.3% |
| SpatialViz-Bench | 33.9% | — |
Multilingual GPT-6 Sol leads
Claude 3.7 Sonnet: 44.1 (#179), GPT-6 Sol: 50.5 (#118)
| Benchmark | Claude 3.7 Sonnet | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1296 | 1385 |
| LMArena Chinese | 1299 | 1405 |
| LMArena French | 1303 | 1410 |
| LMArena German | 1301 | 1390 |
| LMArena Japanese | 1267 | 1385 |
| LMArena Korean | 1249 | 1341 |
| LMArena Russian | 1311 | 1401 |
| LMArena Spanish | 1298 | 1384 |
Instruction Following GPT-6 Sol leads
Claude 3.7 Sonnet: 72.9 (#125), GPT-6 Sol: 74.5 (#94)
| Benchmark | Claude 3.7 Sonnet | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1352 | 1412 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), GPT-6 Sol: 43.1 (#108)
| Benchmark | Claude 3.7 Sonnet | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1373 | 1411 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference GPT-6 Sol leads
Claude 3.7 Sonnet: 54.4 (#150), GPT-6 Sol: 71.9 (#18)
| Benchmark | Claude 3.7 Sonnet | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1314 | 1395 |
| LMArena Creative Writing | 1332 | 1378 |
| EQ-Bench Creative Writing | 1412 | 2125 |
| LMArena Multi-Turn | 1339 | 1412 |
| Short-Story Creative Writing | 81.1% | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 39.5 on the Noometry Index.
Is Claude 3.7 Sonnet or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 40.6 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and GPT-6 Sol share?
24 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and GPT-6 Sol has 45.