Model comparison
Claude 3.5 Sonnet vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 61.8 to 34.6 on the Noometry Index.
Last verified . 23 shared benchmarks.
Summary
- They share 23 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 0 categories and GPT-6 Sol in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Sol leads 87.2 to 19.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 100% for GPT-6 Sol.
Side by side
| Claude 3.5 Sonnet | GPT-6 Sol | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 34.6 | 61.8 |
| Released | 2024-06-20 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $10 |
| Results tracked | 60 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
Claude 3.5 Sonnet: 39.0 (#165), GPT-6 Sol: 60.1 (#11)
| Benchmark | Claude 3.5 Sonnet | GPT-6 Sol |
|---|---|---|
| LMArena Coding | 1342 | 1447 |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| Aider Polyglot | 51.6% | — |
| LMArena WebDev | — | 1688 |
| SciCode | — | 57.6% |
| GSO | 4.6% | — |
| WeirdML | 40% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| ALE-Bench | — | 2,462 |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use GPT-6 Sol leads
Claude 3.5 Sonnet: 32.3 (#67), GPT-6 Sol: 37.2 (#36)
| Benchmark | Claude 3.5 Sonnet | GPT-6 Sol |
|---|---|---|
| APEX-Agents | — | 54.3% |
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| GDP.pdf | — | 26.4% |
| METR Time Horizons | 45.2% | — |
| Vending-Bench 2 | — | 14,428 |
Reasoning GPT-6 Sol leads
Claude 3.5 Sonnet: 23.1 (#183), GPT-6 Sol: 74.0 (#9)
| Benchmark | Claude 3.5 Sonnet | GPT-6 Sol |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1418 |
| DTBench | 67.8% | 97.3% |
| Epoch Capabilities Index | 133.55 | 162.72 |
| ARC-AGI-2 | — | 89.6% |
| SimpleBench | 41.4% | — |
| NYT Connections (extended) | — | 90.1% |
| ARC-AGI-1 | — | 95.5% |
| CritPt | — | 30.9% |
| EnigmaEval | 0.9% | — |
| EBR-Bench | — | 53.3% |
| LiveBench Reasoning | 56.7% | — |
| Mystery Game Puzzles | — | 56% |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 59.1% |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math GPT-6 Sol leads
Claude 3.5 Sonnet: 19.2 (#288), GPT-6 Sol: 87.2 (#7)
| Benchmark | Claude 3.5 Sonnet | GPT-6 Sol |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 100% |
| LMArena Math | 1307 | 1402 |
| FrontierMath (Tiers 1-3) | — | 89.8% |
| FrontierMath Tier 4 | — | 90% |
| ProofBench | — | 83% |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GPT-6 Sol leads
Claude 3.5 Sonnet: 28.6 (#245), GPT-6 Sol: 64.8 (#15)
| Benchmark | Claude 3.5 Sonnet | GPT-6 Sol |
|---|---|---|
| GPQA Diamond | 55.3% | 94.3% |
| LMArena Expert | 1265 | 1439 |
| Humanity's Last Exam | 4.1% | — |
| SimpleQA Verified | — | 60.7% |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| Vectara Hallucination Rate | — | 6.5% |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal GPT-6 Sol leads
Claude 3.5 Sonnet: 26.5 (#120), GPT-6 Sol: 47.6 (#10)
| Benchmark | Claude 3.5 Sonnet | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 1125 | 1245 |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
| Blueprint-Bench 2 | — | 36.9% |
| Furniture Assembly | — | 58.3% |
Multilingual GPT-6 Sol leads
Claude 3.5 Sonnet: 43.2 (#185), GPT-6 Sol: 50.5 (#118)
| Benchmark | Claude 3.5 Sonnet | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1283 | 1385 |
| LMArena Chinese | 1272 | 1405 |
| LMArena French | 1305 | 1410 |
| LMArena German | 1297 | 1390 |
| LMArena Japanese | 1234 | 1385 |
| LMArena Korean | 1200 | 1341 |
| LMArena Russian | 1306 | 1401 |
| LMArena Spanish | 1290 | 1384 |
Instruction Following GPT-6 Sol leads
Claude 3.5 Sonnet: 68.8 (#182), GPT-6 Sol: 74.5 (#94)
| Benchmark | Claude 3.5 Sonnet | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1297 | 1412 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context GPT-6 Sol leads
Claude 3.5 Sonnet: 39.9 (#167), GPT-6 Sol: 43.1 (#108)
| Benchmark | Claude 3.5 Sonnet | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1311 | 1411 |
Writing & Preference GPT-6 Sol leads
Claude 3.5 Sonnet: 52.9 (#164), GPT-6 Sol: 71.9 (#18)
| Benchmark | Claude 3.5 Sonnet | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1298 | 1395 |
| LMArena Creative Writing | 1292 | 1378 |
| EQ-Bench Creative Writing | 1451 | 2125 |
| LMArena Multi-Turn | 1326 | 1412 |
| Short-Story Creative Writing | 80.3% | — |
| WildBench | 79.2% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 39.0 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and GPT-6 Sol share?
23 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and GPT-6 Sol has 45.