Model comparison
GPT-4.1 nano vs o1
o1 is the stronger model overall, scoring 40.9 to 27.9 on the Noometry Index. GPT-4.1 nano costs 150× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. GPT-4.1 nano scores higher in 1 category and o1 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in long context, where o1 leads 50.3 to 23.7.
- The biggest single-benchmark swing is Fiction.LiveBench: 25% for GPT-4.1 nano and 83.3% for o1.
- GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $15 / $60 for o1.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 200K.
Side by side
| GPT-4.1 nano | o1 | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 27.9 | 40.9 |
| Released | 2025-04-14 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 33K | 100K |
| Input $ / M tokens | $0.10 | $15 |
| Output $ / M tokens | $0.40 | $60 |
| Results tracked | 38 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
GPT-4.1 nano: 24.1 (#330), o1: 46.1 (#70)
| Benchmark | GPT-4.1 nano | o1 |
|---|---|---|
| Aider Polyglot | 8.9% | 61.7% |
| WeirdML | 19% | 47.6% |
| LMArena Coding | 1306 | 1367 |
| SciCode | 25.9% | — |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use GPT-4.1 nano leads
GPT-4.1 nano: 26.5 (#104), o1: 24.6 (#117)
| Benchmark | GPT-4.1 nano | o1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 33% | — |
| Cybench | — | 10% |
| METR Time Horizons | — | 51.1% |
Reasoning o1 leads
GPT-4.1 nano: 8.5 (#349), o1: 27.9 (#111)
| Benchmark | GPT-4.1 nano | o1 |
|---|---|---|
| ARC-AGI-1 | 0% | 30.7% |
| LMArena Hard Prompts | 1286 | 1371 |
| DTBench | 52.5% | 74.7% |
| LMCA | 5.5% | 22.3% |
| Epoch Capabilities Index | 129.62 | 141.91 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | — | 41.7% |
| Kagi LLM Benchmark | 33.3% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 15% |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| LiveBench Data Analysis | — | 65.5% |
| LiveBench | — | 75.7% |
Math o1 leads
GPT-4.1 nano: 26.9 (#252), o1: 36.1 (#175)
| Benchmark | GPT-4.1 nano | o1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 28.9% | 73.3% |
| LMArena Math | 1274 | 1388 |
| MATH Level 5 | 70% | 94.7% |
| FrontierMath (Feb 2025 set) | 1% | 9.3% |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| Omni-MATH | 36.7% | — |
| LiveBench Math | — | 80.3% |
Knowledge o1 leads
GPT-4.1 nano: 21.8 (#273), o1: 41.5 (#110)
| Benchmark | GPT-4.1 nano | o1 |
|---|---|---|
| GPQA Diamond | 48.9% | 76.8% |
| SimpleQA Verified | 6% | 41.1% |
| LMArena Expert | 1272 | 1361 |
| Humanity's Last Exam | — | 8% |
| MMLU-Pro | 55% | — |
| Confabulations | — | 11.7% |
| GPQA (HELM) | 50.7% | — |
Multimodal o1 leads
GPT-4.1 nano: 29.2 (#113), o1: 34.2 (#93)
| Benchmark | GPT-4.1 nano | o1 |
|---|---|---|
| LMArena Vision | 1063 | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual o1 leads
GPT-4.1 nano: 41.6 (#205), o1: 48.6 (#142)
| Benchmark | GPT-4.1 nano | o1 |
|---|---|---|
| LMArena Non-English | 1260 | 1358 |
| LMArena Chinese | 1270 | 1394 |
| LMArena German | 1288 | 1337 |
| LMArena Japanese | 1198 | 1346 |
| LMArena Russian | 1261 | 1356 |
| LMArena French | — | 1344 |
| LMArena Korean | — | 1396 |
| LMArena Spanish | — | 1345 |
Instruction Following o1 leads
GPT-4.1 nano: 67.8 (#193), o1: 74.8 (#86)
| Benchmark | GPT-4.1 nano | o1 |
|---|---|---|
| LMArena Instruction Following | 1267 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
| IFEval | 84.3% | — |
Long Context o1 leads
GPT-4.1 nano: 23.7 (#296), o1: 50.3 (#9)
| Benchmark | GPT-4.1 nano | o1 |
|---|---|---|
| Fiction.LiveBench | 25% | 83.3% |
| LMArena Longer Query | 1283 | 1378 |
Writing & Preference o1 leads
GPT-4.1 nano: 40.5 (#243), o1: 55.6 (#144)
| Benchmark | GPT-4.1 nano | o1 |
|---|---|---|
| LMArena Text | 1285 | 1366 |
| LMArena Creative Writing | 1260 | 1348 |
| LMArena Multi-Turn | 1277 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| EQ-Bench Creative Writing | 946 | — |
| WildBench | 81.2% | — |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is GPT-4.1 nano better than o1?
o1 is the stronger model overall, scoring 40.9 to 27.9 on the Noometry Index. GPT-4.1 nano costs 150× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 nano or o1?
GPT-4.1 nano is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; o1 lists at $15 and $60.
Is GPT-4.1 nano or o1 better for coding?
o1 scores higher on coding benchmarks: 46.1 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 GPT-4.1 nano and o1 share?
27 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and o1 has 52.