# GPT-4.1 nano vs o4-mini

> o4-mini is the stronger model overall, scoring 41.6 to 27.7 on the Noometry Index. GPT-4.1 nano costs 11× less per token, which makes it the better buy when o4-mini's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-4-1-nano-vs-o4-mini
- Last updated: 2026-10-10
- Shared benchmarks: 36

## Summary

- They share 36 benchmarks with published results for both. GPT-4.1 nano scores higher in 0 categories and o4-mini in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in long context, where o4-mini leads 45.5 to 23.7.
- The biggest single-benchmark swing is Aider Polyglot: 8.9% for GPT-4.1 nano and 72% for o4-mini.
- GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 200K.

## Snapshot

| | GPT-4.1 nano | o4-mini |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 27.7 | 41.6 |
| Rank | 322 | 119 |
| Context | 1.05M | 200K |
| Input $/M | $0.10 | $1.10 |
| Output $/M | $0.40 | $4.40 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4.1 nano: 23.8 (#325)
- o4-mini: 41.6 (#110)

| Benchmark | GPT-4.1 nano | o4-mini |
|---|---|---|
| Aider Polyglot | 8.9% | 72% |
| WeirdML | 19% | 52.6% |
| LMArena Coding | 1306 | 1369 |
| SWE-bench Verified (bash only) | — | 45% |
| SciCode | 25.9% | — |
| GSO | — | 3.6% |
| CadEval | — | 62% |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |

## Agentic & Tool Use

- GPT-4.1 nano: 26.3 (#98)
- o4-mini: 32.3 (#57)

| Benchmark | GPT-4.1 nano | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 33% | 53.2% |
| GDPval | — | 25.3% |
| METR Time Horizons | — | 63.9% |

## Reasoning

- GPT-4.1 nano: 8.6 (#344)
- o4-mini: 24.6 (#143)

| Benchmark | GPT-4.1 nano | o4-mini |
|---|---|---|
| ARC-AGI-2 | 0% | 6.1% |
| Kagi LLM Benchmark | 33.3% | 67.6% |
| ARC-AGI-1 | 0% | 58.7% |
| CritPt | 0% | 0.6% |
| LMArena Hard Prompts | 1286 | 1351 |
| DTBench | 52.5% | 77.6% |
| LMCA | 5.5% | 26.5% |
| Epoch Capabilities Index | 129.62 | 145.63 |
| SimpleBench | — | 38.7% |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| Mystery Game Puzzles | — | 5% |
| ForecastBench | — | 61.8 |

## Math

- GPT-4.1 nano: 25.5 (#246)
- o4-mini: 40.2 (#79)

| Benchmark | GPT-4.1 nano | o4-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 28.9% | 81.7% |
| Omni-MATH | 36.7% | 72% |
| LMArena Math | 1274 | 1390 |
| MATH Level 5 | 70% | 97.8% |
| FrontierMath (Feb 2025 set) | 1% | 24.8% |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| FrontierMath Tier 4 (v1) | — | 6.3% |

## Knowledge

- GPT-4.1 nano: 21.8 (#268)
- o4-mini: 43.5 (#83)

| Benchmark | GPT-4.1 nano | o4-mini |
|---|---|---|
| GPQA Diamond | 48.9% | 79.6% |
| SimpleQA Verified | 6% | 19.6% |
| MMLU-Pro | 55% | 82% |
| GPQA (HELM) | 50.7% | 73.5% |
| LMArena Expert | 1272 | 1344 |
| Humanity's Last Exam | — | 18.1% |
| Confabulations | — | 15.8% |
| Vectara Hallucination Rate | — | 18.6% |

## Multimodal

- GPT-4.1 nano: 28.6 (#108)
- o4-mini: 39.5 (#46)

| Benchmark | GPT-4.1 nano | o4-mini |
|---|---|---|
| LMArena Vision | 1063 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |

## Multilingual

- GPT-4.1 nano: 41.8 (#200)
- o4-mini: 47.2 (#149)

| Benchmark | GPT-4.1 nano | o4-mini |
|---|---|---|
| LMArena Non-English | 1260 | 1336 |
| LMArena Chinese | 1270 | 1355 |
| LMArena German | 1288 | 1336 |
| LMArena Japanese | 1199 | 1308 |
| LMArena Russian | 1261 | 1334 |
| LMArena French | — | 1362 |
| LMArena Korean | — | 1313 |
| LMArena Spanish | — | 1346 |

## Instruction Following

- GPT-4.1 nano: 68.0 (#188)
- o4-mini: 75.4 (#63)

| Benchmark | GPT-4.1 nano | o4-mini |
|---|---|---|
| IFEval | 84.3% | 92.8% |
| LMArena Instruction Following | 1267 | 1321 |

## Long Context

- GPT-4.1 nano: 23.7 (#291)
- o4-mini: 45.5 (#31)

| Benchmark | GPT-4.1 nano | o4-mini |
|---|---|---|
| Fiction.LiveBench | 25% | 77.8% |
| LMArena Longer Query | 1283 | 1315 |

## Writing & Preference

- GPT-4.1 nano: 40.7 (#238)
- o4-mini: 54.2 (#148)

| Benchmark | GPT-4.1 nano | o4-mini |
|---|---|---|
| LMArena Text | 1285 | 1353 |
| LMArena Creative Writing | 1260 | 1294 |
| WildBench | 81.2% | 85.4% |
| LMArena Multi-Turn | 1277 | 1350 |
| Short-Story Creative Writing | — | 75% |
| EQ-Bench Creative Writing | 946 | — |

## FAQ

### Is GPT-4.1 nano better than o4-mini?

o4-mini is the stronger model overall, scoring 41.6 to 27.7 on the Noometry Index. GPT-4.1 nano costs 11× less per token, which makes it the better buy when o4-mini's lead doesn't matter for your workload.

### Which is cheaper, GPT-4.1 nano or o4-mini?

GPT-4.1 nano is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; o4-mini lists at $1.10 and $4.40.

### Is GPT-4.1 nano or o4-mini better for coding?

o4-mini scores higher on coding benchmarks: 41.6 versus 23.8 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 o4-mini share?

36 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and o4-mini has 60.