# GPT-4.1 nano vs Mistral Small

> Mistral Small is the stronger model overall, scoring 33.1 to 27.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-1-nano-vs-mistral-small
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. GPT-4.1 nano scores higher in 2 categories and Mistral Small in 8 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in long context, where Mistral Small leads 40.4 to 23.7.
- The biggest single-benchmark swing is MATH Level 5: 70% for GPT-4.1 nano and 46.8% for Mistral Small.
- GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.15 / $0.60 for Mistral Small.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 256K.
- Mistral Small has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4.1 nano | Mistral Small |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 27.7 | 33.1 |
| Rank | 322 | 238 |
| Context | 1.05M | 256K |
| Input $/M | $0.10 | $0.15 |
| Output $/M | $0.40 | $0.60 |
| Weights | Proprietary | Open |

## Coding

- GPT-4.1 nano: 23.8 (#325)
- Mistral Small: 33.5 (#242)

| Benchmark | GPT-4.1 nano | Mistral Small |
|---|---|---|
| SciCode | 25.9% | 26.5% |
| LMArena Coding | 1306 | 1363 |
| Aider Polyglot | 8.9% | — |
| WeirdML | 19% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |

## Agentic & Tool Use

- GPT-4.1 nano: 26.3 (#98)
- Mistral Small: 27.9 (#87)

| Benchmark | GPT-4.1 nano | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | 33% | 37.1% |

## Reasoning

- GPT-4.1 nano: 8.6 (#344)
- Mistral Small: 19.3 (#238)

| Benchmark | GPT-4.1 nano | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 33.3% | 37.8% |
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1286 | 1336 |
| DTBench | 52.5% | 70.9% |
| LMCA | 5.5% | 20.6% |
| ARC-AGI-2 | 0% | — |
| ARC-AGI-1 | 0% | — |
| LiveBench Reasoning | — | 44.8% |
| LiveBench Data Analysis | — | 53.7% |
| Epoch Capabilities Index | 129.62 | — |
| LiveBench | — | 44% |

## Math

- GPT-4.1 nano: 25.5 (#246)
- Mistral Small: 15.4 (#287)

| Benchmark | GPT-4.1 nano | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 28.9% | 5.8% |
| LMArena Math | 1274 | 1341 |
| MATH Level 5 | 70% | 46.8% |
| Omni-MATH | 36.7% | — |
| LiveBench Math | — | 39.9% |
| FrontierMath (Feb 2025 set) | 1% | — |

## Knowledge

- GPT-4.1 nano: 21.8 (#268)
- Mistral Small: 30.9 (#214)

| Benchmark | GPT-4.1 nano | Mistral Small |
|---|---|---|
| GPQA Diamond | 48.9% | 47.5% |
| LMArena Expert | 1272 | 1293 |
| SimpleQA Verified | 6% | — |
| MMLU-Pro | 55% | — |
| Vectara Hallucination Rate | — | 5.1% |
| GPQA (HELM) | 50.7% | — |
| MMLU | — | 68.7% |

## Multimodal

- GPT-4.1 nano: 28.6 (#108)
- Mistral Small: 32.9 (#91)

| Benchmark | GPT-4.1 nano | Mistral Small |
|---|---|---|
| LMArena Vision | 1063 | 1142 |

## Multilingual

- GPT-4.1 nano: 41.8 (#200)
- Mistral Small: 45.7 (#164)

| Benchmark | GPT-4.1 nano | Mistral Small |
|---|---|---|
| LMArena Non-English | 1260 | 1315 |
| LMArena Chinese | 1270 | 1342 |
| LMArena German | 1288 | 1341 |
| LMArena Japanese | 1199 | 1275 |
| LMArena Russian | 1261 | 1324 |
| LMArena French | — | 1337 |
| LMArena Korean | — | 1260 |
| LMArena Spanish | — | 1346 |

## Instruction Following

- GPT-4.1 nano: 68.0 (#188)
- Mistral Small: 66.6 (#204)

| Benchmark | GPT-4.1 nano | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1267 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
| IFEval | 84.3% | — |

## Long Context

- GPT-4.1 nano: 23.7 (#291)
- Mistral Small: 40.4 (#151)

| Benchmark | GPT-4.1 nano | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1283 | 1327 |
| Fiction.LiveBench | 25% | — |

## Writing & Preference

- GPT-4.1 nano: 40.7 (#238)
- Mistral Small: 52.6 (#165)

| Benchmark | GPT-4.1 nano | Mistral Small |
|---|---|---|
| LMArena Text | 1285 | 1338 |
| LMArena Creative Writing | 1260 | 1304 |
| LMArena Multi-Turn | 1277 | 1344 |
| EQ-Bench Creative Writing | 946 | — |
| WildBench | 81.2% | — |
| LiveBench Language | — | 30.5% |

## FAQ

### Is GPT-4.1 nano better than Mistral Small?

Mistral Small is the stronger model overall, scoring 33.1 to 27.7 on the Noometry Index.

### Which is cheaper, GPT-4.1 nano or Mistral Small?

GPT-4.1 nano is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Mistral Small lists at $0.15 and $0.60.

### Is GPT-4.1 nano or Mistral Small better for coding?

Mistral Small scores higher on coding benchmarks: 33.5 versus 23.8 in the Noometry coding category.

### Which has the bigger context window?

GPT-4.1 nano does, with 1.05M tokens against 256K.

### How many benchmarks do GPT-4.1 nano and Mistral Small share?

24 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and Mistral Small has 39.