Model comparison
Claude 3.5 Sonnet vs GPT-5 Nano
Claude 3.5 Sonnet is the stronger model overall, scoring 34.6 to 33.5 on the Noometry Index.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 5 categories and GPT-5 Nano in 5 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude 3.5 Sonnet leads 52.9 to 39.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 81.1% for GPT-5 Nano.
Side by side
| Claude 3.5 Sonnet | GPT-5 Nano | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 34.6 | 33.5 |
| Released | 2024-06-20 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.40 |
| Results tracked | 60 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.0 (#165), GPT-5 Nano: 33.6 (#254)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Nano |
|---|---|---|
| WeirdML | 40% | 38.1% |
| LMArena Coding | 1342 | 1351 |
| SWE-bench Verified (bash only) | — | 34.8% |
| Aider Polyglot | 51.6% | — |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| ALE-Bench | — | 718.67 |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 32.3 (#67), GPT-5 Nano: 25.8 (#106)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Nano |
|---|---|---|
| Terminal-Bench | — | 21.8% |
| Berkeley Function Calling Leaderboard | — | 51.5% |
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 23.1 (#183), GPT-5 Nano: 16.3 (#306)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Nano |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1328 |
| DTBench | 67.8% | 62.7% |
| Epoch Capabilities Index | 133.55 | 139.38 |
| ForecastBench | 60.7 | 59.1 |
| ARC-AGI-2 | — | 2.6% |
| SimpleBench | 41.4% | — |
| Kagi LLM Benchmark | — | 62.2% |
| ARC-AGI-1 | — | 20.7% |
| Chess Puzzles | — | 27% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| Mystery Game Puzzles | — | 9% |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 7.9% |
| LiveBench | 59% | — |
Math GPT-5 Nano leads
Claude 3.5 Sonnet: 19.2 (#288), GPT-5 Nano: 29.4 (#241)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 81.1% |
| Omni-MATH | 27.6% | 54.6% |
| LMArena Math | 1307 | 1317 |
| MATH Level 5 | 56.9% | 95.2% |
| FrontierMath (Feb 2025 set) | 2.1% | 8.3% |
| FrontierMath Tier 4 (v1) | 0% | 2.1% |
| FrontierMath (Tiers 1-3) | — | 20% |
| FrontierMath Tier 4 | — | 2.4% |
| ProofBench | — | 12% |
| LiveBench Math | 52.3% | — |
Knowledge GPT-5 Nano leads
Claude 3.5 Sonnet: 28.6 (#245), GPT-5 Nano: 35.9 (#178)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Nano |
|---|---|---|
| GPQA Diamond | 55.3% | 69.4% |
| MMLU-Pro | 77.7% | 77.8% |
| GPQA (HELM) | 56.5% | 67.9% |
| LMArena Expert | 1265 | 1321 |
| Humanity's Last Exam | 4.1% | — |
| SimpleQA Verified | — | 11.7% |
| Confabulations | 19.9% | — |
| Vectara Hallucination Rate | — | 10.5% |
| MMLU | 87.3% | — |
Multimodal GPT-5 Nano leads
Claude 3.5 Sonnet: 26.5 (#120), GPT-5 Nano: 31.3 (#108)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Nano |
|---|---|---|
| LMArena Vision | 1125 | 1159 |
| VPCT | 33% | 37.2% |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
Multilingual GPT-5 Nano leads
Claude 3.5 Sonnet: 43.2 (#185), GPT-5 Nano: 45.3 (#172)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Nano |
|---|---|---|
| LMArena Non-English | 1283 | 1313 |
| LMArena Chinese | 1272 | 1356 |
| LMArena German | 1297 | 1327 |
| LMArena Japanese | 1234 | 1226 |
| LMArena Korean | 1200 | 1269 |
| LMArena Russian | 1306 | 1296 |
| LMArena Spanish | 1290 | 1360 |
| LMArena French | 1305 | — |
Instruction Following GPT-5 Nano leads
Claude 3.5 Sonnet: 68.8 (#182), GPT-5 Nano: 75.0 (#79)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Nano |
|---|---|---|
| IFEval | 85.5% | 93.2% |
| LMArena Instruction Following | 1297 | 1306 |
| LiveBench Instruction Following | 69.3% | — |
Long Context Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.9 (#167), GPT-5 Nano: 31.3 (#281)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Nano |
|---|---|---|
| LMArena Longer Query | 1311 | 1312 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 52.9 (#164), GPT-5 Nano: 39.1 (#249)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Nano |
|---|---|---|
| LMArena Text | 1298 | 1320 |
| LMArena Creative Writing | 1292 | 1249 |
| EQ-Bench Creative Writing | 1451 | 705 |
| WildBench | 79.2% | 80.6% |
| LMArena Multi-Turn | 1326 | 1311 |
| Short-Story Creative Writing | 80.3% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than GPT-5 Nano?
Claude 3.5 Sonnet is the stronger model overall, scoring 34.6 to 33.5 on the Noometry Index.
Is Claude 3.5 Sonnet or GPT-5 Nano better for coding?
Claude 3.5 Sonnet scores higher on coding benchmarks: 39.0 versus 33.6 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and GPT-5 Nano share?
33 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and GPT-5 Nano has 49.