# GPT-5 Nano vs Mistral 7B

> GPT-5 Nano is the stronger model overall, scoring 33.4 to 22.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-nano-vs-mistral-7b
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. GPT-5 Nano scores higher in 7 categories and Mistral 7B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5 Nano leads 35.8 to 7.3.
- The biggest single-benchmark swing is MATH Level 5: 95.2% for GPT-5 Nano and 3.7% for Mistral 7B.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $0.25 / $0.25 for Mistral 7B.
- GPT-5 Nano accepts more context: 400K tokens versus 8K.
- Mistral 7B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5 Nano | Mistral 7B |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 33.4 | 22.9 |
| Rank | 234 | 346 |
| Context | 400K | 8K |
| Input $/M | $0.05 | $0.25 |
| Output $/M | $0.40 | $0.25 |
| Weights | Proprietary | Open |

## Coding

- GPT-5 Nano: 33.3 (#248)
- Mistral 7B: 25.9 (#321)

| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| LMArena Coding | 1351 | 1082 |
| SWE-bench Verified (bash only) | 34.8% | — |
| WeirdML | 38.1% | — |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
| ALE-Bench | 718.67 | — |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |

## Agentic & Tool Use

- GPT-5 Nano: 25.6 (#99)
- Mistral 7B: —

| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |

## Reasoning

- GPT-5 Nano: 16.4 (#291)
- Mistral 7B: 12.6 (#331)

| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| Chess Puzzles | 27% | 0% |
| LMArena Hard Prompts | 1329 | 1067 |
| DTBench | 62.7% | 42.5% |
| Epoch Capabilities Index | 139.39 | 111.97 |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| ARC-AGI-1 | 20.7% | — |
| Mystery Game Puzzles | 9% | — |
| LMCA | 7.9% | — |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| ForecastBench | 59.1 | — |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |

## Math

- GPT-5 Nano: 29.1 (#221)
- Mistral 7B: 7.6 (#319)

| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 81.1% | 0.3% |
| LMArena Math | 1318 | 1085 |
| MATH Level 5 | 95.2% | 3.7% |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
| GSM8K | — | 54.4% |

## Knowledge

- GPT-5 Nano: 35.8 (#166)
- Mistral 7B: 7.3 (#306)

| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| GPQA Diamond | 69.4% | 15.2% |
| LMArena Expert | 1321 | 1036 |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| MMLU | — | 62.5% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |

## Multimodal

- GPT-5 Nano: 30.7 (#102)
- Mistral 7B: —

| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |

## Multilingual

- GPT-5 Nano: 45.5 (#167)
- Mistral 7B: 26.0 (#278)

| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1313 | 1012 |
| LMArena Chinese | 1355 | 1009 |
| LMArena German | 1329 | 987 |
| LMArena Russian | 1296 | 1018 |
| LMArena Spanish | 1360 | 1026 |
| LMArena French | — | 1036 |
| LMArena Japanese | — | 878 |
| LMArena Korean | 1269 | — |

## Instruction Following

- GPT-5 Nano: 75.2 (#72)
- Mistral 7B: 54.5 (#275)

| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1306 | 1060 |
| IFEval | 93.2% | — |

## Long Context

- GPT-5 Nano: 31.3 (#275)
- Mistral 7B: 32.2 (#266)

| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1313 | 1060 |
| Fiction.LiveBench | 44.4% | — |

## Writing & Preference

- GPT-5 Nano: 39.4 (#244)
- Mistral 7B: 30.9 (#281)

| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| LMArena Text | 1320 | 1090 |
| LMArena Creative Writing | 1250 | 1068 |
| LMArena Multi-Turn | 1311 | 1062 |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |

## FAQ

### Is GPT-5 Nano better than Mistral 7B?

GPT-5 Nano is the stronger model overall, scoring 33.4 to 22.9 on the Noometry Index.

### Which is cheaper, GPT-5 Nano or Mistral 7B?

GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Mistral 7B lists at $0.25 and $0.25.

### Is GPT-5 Nano or Mistral 7B better for coding?

GPT-5 Nano scores higher on coding benchmarks: 33.3 versus 25.9 in the Noometry coding category.

### Which has the bigger context window?

GPT-5 Nano does, with 400K tokens against 8K.

### How many benchmarks do GPT-5 Nano and Mistral 7B share?

20 benchmarks have published results for both models. GPT-5 Nano has 48 scored results on Noometry and Mistral 7B has 37.