Model comparison
Claude Sonnet 4 vs GPT-4.1 nano
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 27.9 on the Noometry Index. GPT-4.1 nano costs 34× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Last verified . 36 shared benchmarks.
Summary
- They share 36 benchmarks with published results for both. Claude Sonnet 4 scores higher in 9 categories and GPT-4.1 nano in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Sonnet 4 leads 41.8 to 21.8.
- The biggest single-benchmark swing is Aider Polyglot: 61.3% for Claude Sonnet 4 and 8.9% for GPT-4.1 nano.
- GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Sonnet 4 | GPT-4.1 nano | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 40.8 | 27.9 |
| Released | 2025-05-22 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 64K | 33K |
| Input $ / M tokens | $3 | $0.10 |
| Output $ / M tokens | $15 | $0.40 |
| Results tracked | 58 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 43.5 (#88), GPT-4.1 nano: 24.1 (#330)
| Benchmark | Claude Sonnet 4 | GPT-4.1 nano |
|---|---|---|
| Aider Polyglot | 61.3% | 8.9% |
| SciCode | 40% | 25.9% |
| WeirdML | 46.1% | 19% |
| LMArena Coding | 1414 | 1306 |
| SWE-bench Verified (bash only) | 64.9% | — |
| GSO | 4.9% | — |
| ALE-Bench | 655.35 | — |
Agentic & Tool Use Claude Sonnet 4 leads
Claude Sonnet 4: 38.5 (#31), GPT-4.1 nano: 26.5 (#104)
| Benchmark | Claude Sonnet 4 | GPT-4.1 nano |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 33% |
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Claude Sonnet 4 leads
Claude Sonnet 4: 22.9 (#187), GPT-4.1 nano: 8.5 (#349)
| Benchmark | Claude Sonnet 4 | GPT-4.1 nano |
|---|---|---|
| ARC-AGI-2 | 5.9% | 0% |
| Kagi LLM Benchmark | 73% | 33.3% |
| ARC-AGI-1 | 40% | 0% |
| CritPt | 0.3% | 0% |
| LMArena Hard Prompts | 1372 | 1286 |
| DTBench | 77.1% | 52.5% |
| LMCA | 29% | 5.5% |
| Epoch Capabilities Index | 141.69 | 129.62 |
| SimpleBench | 45.5% | — |
| EnigmaEval | 3.1% | — |
| ForecastBench | 60.2 | — |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), GPT-4.1 nano: 26.9 (#252)
| Benchmark | Claude Sonnet 4 | GPT-4.1 nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 28.9% |
| Omni-MATH | 60.2% | 36.7% |
| LMArena Math | 1375 | 1274 |
| MATH Level 5 | 84.4% | 70% |
| FrontierMath (Feb 2025 set) | 4.1% | 1% |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.8 (#108), GPT-4.1 nano: 21.8 (#273)
| Benchmark | Claude Sonnet 4 | GPT-4.1 nano |
|---|---|---|
| GPQA Diamond | 79.2% | 48.9% |
| MMLU-Pro | 84.3% | 55% |
| GPQA (HELM) | 70.6% | 50.7% |
| LMArena Expert | 1372 | 1272 |
| Humanity's Last Exam | 7.8% | — |
| SimpleQA Verified | — | 6% |
| Confabulations | 13.2% | — |
| Vectara Hallucination Rate | 10.3% | — |
Multimodal GPT-4.1 nano leads
Claude Sonnet 4: 26.2 (#121), GPT-4.1 nano: 29.2 (#113)
| Benchmark | Claude Sonnet 4 | GPT-4.1 nano |
|---|---|---|
| LMArena Vision | 1191 | 1063 |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Claude Sonnet 4 leads
Claude Sonnet 4: 46.7 (#156), GPT-4.1 nano: 41.6 (#205)
| Benchmark | Claude Sonnet 4 | GPT-4.1 nano |
|---|---|---|
| LMArena Non-English | 1333 | 1260 |
| LMArena Chinese | 1350 | 1270 |
| LMArena German | 1331 | 1288 |
| LMArena Japanese | 1302 | 1198 |
| LMArena Russian | 1355 | 1261 |
| LMArena French | 1363 | — |
| LMArena Korean | 1291 | — |
| LMArena Spanish | 1357 | — |
Instruction Following Claude Sonnet 4 leads
Claude Sonnet 4: 71.7 (#145), GPT-4.1 nano: 67.8 (#193)
| Benchmark | Claude Sonnet 4 | GPT-4.1 nano |
|---|---|---|
| IFEval | 84% | 84.3% |
| LMArena Instruction Following | 1376 | 1267 |
Long Context Claude Sonnet 4 leads
Claude Sonnet 4: 33.7 (#259), GPT-4.1 nano: 23.7 (#296)
| Benchmark | Claude Sonnet 4 | GPT-4.1 nano |
|---|---|---|
| Fiction.LiveBench | 46.9% | 25% |
| LMArena Longer Query | 1398 | 1283 |
Writing & Preference Claude Sonnet 4 leads
Claude Sonnet 4: 57.1 (#132), GPT-4.1 nano: 40.5 (#243)
| Benchmark | Claude Sonnet 4 | GPT-4.1 nano |
|---|---|---|
| LMArena Text | 1351 | 1285 |
| LMArena Creative Writing | 1345 | 1260 |
| EQ-Bench Creative Writing | 1483 | 946 |
| WildBench | 83.8% | 81.2% |
| LMArena Multi-Turn | 1376 | 1277 |
| Short-Story Creative Writing | 81.4% | — |
Frequently asked questions
Is Claude Sonnet 4 better than GPT-4.1 nano?
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 27.9 on the Noometry Index. GPT-4.1 nano costs 34× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 4 or GPT-4.1 nano?
GPT-4.1 nano is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or GPT-4.1 nano better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 24.1 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 nano does, with 1.05M tokens against 200K.
How many benchmarks do Claude Sonnet 4 and GPT-4.1 nano share?
36 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and GPT-4.1 nano has 38.