# GPT-5 Nano vs Mistral Medium 3.5

> Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 33.5 on the Noometry Index. GPT-5 Nano costs 22× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-nano-vs-mistral-medium-3-5
- Last updated: 2026-10-12
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. GPT-5 Nano scores higher in 1 category and Mistral Medium 3.5 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium 3.5 leads 58.5 to 39.1.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 62.2% for GPT-5 Nano and 41.4% for Mistral Medium 3.5.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- GPT-5 Nano accepts more context: 400K tokens versus 262K.
- Mistral Medium 3.5 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5 Nano | Mistral Medium 3.5 |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 33.5 | 40.2 |
| Rank | 241 | 152 |
| Context | 400K | 262K |
| Input $/M | $0.05 | $1.50 |
| Output $/M | $0.40 | $7.50 |
| Weights | Proprietary | Open |

## Coding

- GPT-5 Nano: 33.6 (#254)
- Mistral Medium 3.5: 36.0 (#213)

| Benchmark | GPT-5 Nano | Mistral Medium 3.5 |
|---|---|---|
| LMArena Coding | 1351 | 1461 |
| SWE-bench Verified (bash only) | 34.8% | — |
| LMArena WebDev | — | 1264 |
| WeirdML | 38.1% | — |
| ALE-Bench | 718.67 | — |

## Agentic & Tool Use

- GPT-5 Nano: 25.8 (#106)
- Mistral Medium 3.5: —

| Benchmark | GPT-5 Nano | Mistral Medium 3.5 |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |

## Reasoning

- GPT-5 Nano: 16.3 (#306)
- Mistral Medium 3.5: 17.3 (#295)

| Benchmark | GPT-5 Nano | Mistral Medium 3.5 |
|---|---|---|
| Kagi LLM Benchmark | 62.2% | 41.4% |
| LMArena Hard Prompts | 1328 | 1436 |
| Epoch Capabilities Index | 139.38 | 141.35 |
| ARC-AGI-2 | 2.6% | — |
| NYT Connections (extended) | — | 12.9% |
| ARC-AGI-1 | 20.7% | — |
| Chess Puzzles | 27% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 62.7% | — |
| LMCA | 7.9% | — |
| ForecastBench | 59.1 | — |

## Math

- GPT-5 Nano: 29.4 (#241)
- Mistral Medium 3.5: 39.1 (#113)

| Benchmark | GPT-5 Nano | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1317 | 1431 |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 81.1% | — |
| 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: 35.9 (#178)
- Mistral Medium 3.5: 40.0 (#126)

| Benchmark | GPT-5 Nano | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1321 | 1432 |
| GPQA Diamond | 69.4% | — |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |

## Multimodal

- GPT-5 Nano: 31.3 (#108)
- Mistral Medium 3.5: 38.3 (#65)

| Benchmark | GPT-5 Nano | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | 1159 | 1223 |
| VPCT | 37.2% | — |

## Multilingual

- GPT-5 Nano: 45.3 (#172)
- Mistral Medium 3.5: 51.9 (#100)

| Benchmark | GPT-5 Nano | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1313 | 1404 |
| LMArena Chinese | 1356 | 1442 |
| LMArena German | 1327 | 1451 |
| LMArena Korean | 1269 | 1385 |
| LMArena Russian | 1296 | 1395 |
| LMArena Spanish | 1360 | 1409 |
| LMArena French | — | 1448 |
| LMArena Japanese | 1226 | — |

## Instruction Following

- GPT-5 Nano: 75.0 (#79)
- Mistral Medium 3.5: 74.6 (#90)

| Benchmark | GPT-5 Nano | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1306 | 1415 |
| IFEval | 93.2% | — |

## Long Context

- GPT-5 Nano: 31.3 (#281)
- Mistral Medium 3.5: 43.2 (#103)

| Benchmark | GPT-5 Nano | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1312 | 1415 |
| Fiction.LiveBench | 44.4% | — |

## Writing & Preference

- GPT-5 Nano: 39.1 (#249)
- Mistral Medium 3.5: 58.5 (#117)

| Benchmark | GPT-5 Nano | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1320 | 1421 |
| LMArena Creative Writing | 1249 | 1374 |
| LMArena Multi-Turn | 1311 | 1423 |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
| EQ-Bench 4 | — | 993 |

## FAQ

### Is GPT-5 Nano better than Mistral Medium 3.5?

Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 33.5 on the Noometry Index. GPT-5 Nano costs 22× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.

### Which is cheaper, GPT-5 Nano or Mistral Medium 3.5?

GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

### Is GPT-5 Nano or Mistral Medium 3.5 better for coding?

Mistral Medium 3.5 scores higher on coding benchmarks: 36.0 versus 33.6 in the Noometry coding category.

### Which has the bigger context window?

GPT-5 Nano does, with 400K tokens against 262K.

### How many benchmarks do GPT-5 Nano and Mistral Medium 3.5 share?

18 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Mistral Medium 3.5 has 22.