# GPT-5 Nano vs Mistral Small 3

> GPT-5 Nano is the stronger model overall, scoring 33.4 to 30.9 on the Noometry Index. Mistral Small 3 costs 2.4× less per token, which makes it the better buy when GPT-5 Nano's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-nano-vs-mistral-small-3
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. GPT-5 Nano scores higher in 5 categories and Mistral Small 3 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Nano leads 29.1 to 15.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 81.1% for GPT-5 Nano and 6.7% for Mistral Small 3.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.05 / $0.40 for GPT-5 Nano.
- GPT-5 Nano accepts more context: 400K tokens versus 33K.
- Mistral Small 3 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 33.4 | 30.9 |
| Rank | 234 | 268 |
| Context | 400K | 33K |
| Input $/M | $0.05 | $0.05 |
| Output $/M | $0.40 | $0.08 |
| Weights | Proprietary | Open |

## Coding

- GPT-5 Nano: 33.3 (#248)
- Mistral Small 3: 36.0 (#203)

| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1351 | 1246 |
| SWE-bench Verified (bash only) | 34.8% | — |
| WeirdML | 38.1% | — |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |
| ALE-Bench | 718.67 | — |

## Agentic & Tool Use

- GPT-5 Nano: 25.6 (#99)
- Mistral Small 3: —

| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |

## Reasoning

- GPT-5 Nano: 16.4 (#291)
- Mistral Small 3: 18.2 (#269)

| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| Chess Puzzles | 27% | 0% |
| LMArena Hard Prompts | 1329 | 1233 |
| Epoch Capabilities Index | 139.39 | 127.06 |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| ARC-AGI-1 | 20.7% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 62.7% | — |
| LMCA | 7.9% | — |
| ForecastBench | 59.1 | — |

## Math

- GPT-5 Nano: 29.1 (#221)
- Mistral Small 3: 15.3 (#290)

| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 81.1% | 6.7% |
| LMArena Math | 1318 | 1240 |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| MATH Level 5 | 95.2% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GPT-5 Nano: 35.8 (#166)
- Mistral Small 3: 25.0 (#258)

| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 69.4% | 47.3% |
| LMArena Expert | 1321 | 1202 |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Confabulations | — | 25.2% |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |

## Multimodal

- GPT-5 Nano: 30.7 (#102)
- Mistral Small 3: —

| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |

## Multilingual

- GPT-5 Nano: 45.5 (#167)
- Mistral Small 3: 37.5 (#231)

| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1313 | 1198 |
| LMArena Chinese | 1355 | 1204 |
| LMArena German | 1329 | 1211 |
| LMArena Korean | 1269 | 1188 |
| LMArena Russian | 1296 | 1216 |
| LMArena French | — | 1202 |
| LMArena Japanese | — | 1111 |
| LMArena Spanish | 1360 | — |

## Instruction Following

- GPT-5 Nano: 75.2 (#72)
- Mistral Small 3: 63.9 (#224)

| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1306 | 1214 |
| IFEval | 93.2% | — |

## Long Context

- GPT-5 Nano: 31.3 (#275)
- Mistral Small 3: 37.8 (#206)

| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1313 | 1246 |
| Fiction.LiveBench | 44.4% | — |

## Writing & Preference

- GPT-5 Nano: 39.4 (#244)
- Mistral Small 3: 32.4 (#275)

| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1320 | 1234 |
| LMArena Creative Writing | 1250 | 1195 |
| EQ-Bench Creative Writing | 705 | 707 |
| LMArena Multi-Turn | 1311 | 1217 |
| WildBench | 80.6% | — |

## FAQ

### Is GPT-5 Nano better than Mistral Small 3?

GPT-5 Nano is the stronger model overall, scoring 33.4 to 30.9 on the Noometry Index. Mistral Small 3 costs 2.4× less per token, which makes it the better buy when GPT-5 Nano's lead doesn't matter for your workload.

### Which is cheaper, GPT-5 Nano or Mistral Small 3?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; GPT-5 Nano lists at $0.05 and $0.40.

### Is GPT-5 Nano or Mistral Small 3 better for coding?

Mistral Small 3 scores higher on coding benchmarks: 36.0 versus 33.3 in the Noometry coding category.

### Which has the bigger context window?

GPT-5 Nano does, with 400K tokens against 33K.

### How many benchmarks do GPT-5 Nano and Mistral Small 3 share?

19 benchmarks have published results for both models. GPT-5 Nano has 48 scored results on Noometry and Mistral Small 3 has 24.