Model comparison
GPT-4.1 vs GPT-4.1 nano
GPT-4.1 is the stronger model overall, scoring 35.9 to 27.9 on the Noometry Index. GPT-4.1 nano costs 20× less per token, which makes it the better buy when GPT-4.1's lead doesn't matter for your workload.
Last verified . 36 shared benchmarks.
Summary
- They share 36 benchmarks with published results for both. GPT-4.1 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 writing & preference, where GPT-4.1 leads 57.6 to 40.5.
- The biggest single-benchmark swing is Aider Polyglot: 52.4% for GPT-4.1 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 $2 / $8 for GPT-4.1.
Side by side
| GPT-4.1 | GPT-4.1 nano | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 35.9 | 27.9 |
| Released | 2025-04-14 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 33K | 33K |
| Input $ / M tokens | $2 | $0.10 |
| Output $ / M tokens | $8 | $0.40 |
| Results tracked | 52 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.1 leads
GPT-4.1: 34.4 (#238), GPT-4.1 nano: 24.1 (#330)
| Benchmark | GPT-4.1 | GPT-4.1 nano |
|---|---|---|
| Aider Polyglot | 52.4% | 8.9% |
| WeirdML | 39% | 19% |
| LMArena Coding | 1391 | 1306 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| SciCode | — | 25.9% |
| CadEval | 42% | — |
| ALE-Bench | 558.1 | — |
Agentic & Tool Use GPT-4.1 leads
GPT-4.1: 34.7 (#43), GPT-4.1 nano: 26.5 (#104)
| Benchmark | GPT-4.1 | GPT-4.1 nano |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | 33% |
Reasoning GPT-4.1 leads
GPT-4.1: 11.7 (#339), GPT-4.1 nano: 8.5 (#349)
| Benchmark | GPT-4.1 | GPT-4.1 nano |
|---|---|---|
| ARC-AGI-2 | 0.4% | 0% |
| Kagi LLM Benchmark | 52.3% | 33.3% |
| ARC-AGI-1 | 5.5% | 0% |
| LMArena Hard Prompts | 1384 | 1286 |
| DTBench | 68.3% | 52.5% |
| LMCA | 25.6% | 5.5% |
| Epoch Capabilities Index | 136.78 | 129.62 |
| SimpleBench | 27% | — |
| CritPt | — | 0% |
| Chess Puzzles | 6% | — |
| EnigmaEval | 2.2% | — |
| ForecastBench | 61.5 | — |
Math GPT-4.1 nano leads
GPT-4.1: 22.3 (#280), GPT-4.1 nano: 26.9 (#252)
| Benchmark | GPT-4.1 | GPT-4.1 nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 38.3% | 28.9% |
| Omni-MATH | 47.1% | 36.7% |
| LMArena Math | 1370 | 1274 |
| MATH Level 5 | 83% | 70% |
| FrontierMath (Feb 2025 set) | 5.5% | 1% |
| FrontierMath (Tiers 1-3) | 6% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GPT-4.1 leads
GPT-4.1: 37.1 (#160), GPT-4.1 nano: 21.8 (#273)
| Benchmark | GPT-4.1 | GPT-4.1 nano |
|---|---|---|
| GPQA Diamond | 66.9% | 48.9% |
| SimpleQA Verified | 31.1% | 6% |
| MMLU-Pro | 81.1% | 55% |
| GPQA (HELM) | 65.9% | 50.7% |
| LMArena Expert | 1364 | 1272 |
| Humanity's Last Exam | 5.4% | — |
| Vectara Hallucination Rate | 5.6% | — |
Multimodal GPT-4.1 leads
GPT-4.1: 38.2 (#67), GPT-4.1 nano: 29.2 (#113)
| Benchmark | GPT-4.1 | GPT-4.1 nano |
|---|---|---|
| LMArena Vision | 1211 | 1063 |
| GeoBench | 72% | — |
Multilingual GPT-4.1 leads
GPT-4.1: 49.4 (#133), GPT-4.1 nano: 41.6 (#205)
| Benchmark | GPT-4.1 | GPT-4.1 nano |
|---|---|---|
| LMArena Non-English | 1370 | 1260 |
| LMArena Chinese | 1382 | 1270 |
| LMArena German | 1381 | 1288 |
| LMArena Japanese | 1319 | 1198 |
| LMArena Russian | 1377 | 1261 |
| LMArena French | 1382 | — |
| LMArena Korean | 1339 | — |
| LMArena Spanish | 1376 | — |
Instruction Following GPT-4.1 leads
GPT-4.1: 71.3 (#153), GPT-4.1 nano: 67.8 (#193)
| Benchmark | GPT-4.1 | GPT-4.1 nano |
|---|---|---|
| IFEval | 83.8% | 84.3% |
| LMArena Instruction Following | 1367 | 1267 |
Long Context GPT-4.1 leads
GPT-4.1: 40.0 (#163), GPT-4.1 nano: 23.7 (#296)
| Benchmark | GPT-4.1 | GPT-4.1 nano |
|---|---|---|
| Fiction.LiveBench | 63.9% | 25% |
| LMArena Longer Query | 1385 | 1283 |
Writing & Preference GPT-4.1 leads
GPT-4.1: 57.6 (#125), GPT-4.1 nano: 40.5 (#243)
| Benchmark | GPT-4.1 | GPT-4.1 nano |
|---|---|---|
| LMArena Text | 1383 | 1285 |
| LMArena Creative Writing | 1363 | 1260 |
| EQ-Bench Creative Writing | 1420 | 946 |
| WildBench | 85.4% | 81.2% |
| LMArena Multi-Turn | 1398 | 1277 |
Frequently asked questions
Is GPT-4.1 better than GPT-4.1 nano?
GPT-4.1 is the stronger model overall, scoring 35.9 to 27.9 on the Noometry Index. GPT-4.1 nano costs 20× less per token, which makes it the better buy when GPT-4.1's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 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; GPT-4.1 lists at $2 and $8.
Is GPT-4.1 or GPT-4.1 nano better for coding?
GPT-4.1 scores higher on coding benchmarks: 34.4 versus 24.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do GPT-4.1 and GPT-4.1 nano share?
36 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and GPT-4.1 nano has 38.