# Mistral 7B vs Mistral Medium 3.1

> Mistral Medium 3.1 is the stronger model overall, scoring 31.9 to 23.0 on the Noometry Index. Mistral 7B costs 3.2× less per token, which makes it the better buy when Mistral Medium 3.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mistral-7b-vs-mistral-medium-3-1
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in writing & preference, where Mistral Medium 3.1 leads 55.5 to 30.7.
- Mistral 7B is cheaper at $0.25 / $0.25 per million input/output tokens, against $0.40 / $2 for Mistral Medium 3.1.
- Mistral Medium 3.1 accepts more context: 131K tokens versus 8K.
- Mistral 7B has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral 7B | Mistral Medium 3.1 |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 23.0 | 31.9 |
| Rank | 351 | 266 |
| Context | 8K | 131K |
| Input $/M | $0.25 | $0.40 |
| Output $/M | $0.25 | $2 |
| Weights | Open | Proprietary |

## Coding

- Mistral 7B: 26.4 (#326)
- Mistral Medium 3.1: —

| Benchmark | Mistral 7B | Mistral Medium 3.1 |
|---|---|---|
| BigCodeBench Instruct | 19.5% | — |
| LMArena Coding | 1082 | — |
| BigCodeBench Complete | 27.3% | — |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |

## Reasoning

- Mistral 7B: 13.1 (#336)
- Mistral Medium 3.1: 10.6 (#341)

| Benchmark | Mistral 7B | Mistral Medium 3.1 |
|---|---|---|
| NYT Connections (extended) | — | 6.5% |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 20.3% |
| LMArena Hard Prompts | 1067 | — |
| DTBench | 42.5% | — |
| Adversarial NLI | 47.1% | — |
| BIG-Bench Hard | 56.1% | — |
| Epoch Capabilities Index | 112.21 | — |
| HellaSwag | 81% | — |
| PIQA | 83% | — |
| WinoGrande | 75.3% | — |

## Math

- Mistral 7B: 8.1 (#325)
- Mistral Medium 3.1: —

| Benchmark | Mistral 7B | Mistral Medium 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.3% | — |
| LMArena Math | 1085 | — |
| MATH Level 5 | 3.7% | — |
| GSM8K | 54.4% | — |

## Knowledge

- Mistral 7B: 7.4 (#311)
- Mistral Medium 3.1: —

| Benchmark | Mistral 7B | Mistral Medium 3.1 |
|---|---|---|
| GPQA Diamond | 15.2% | — |
| LMArena Expert | 1036 | — |
| ARC (AI2) Challenge | 78.6% | — |
| BoolQ | 87.4% | — |
| MMLU | 62.5% | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |

## Multilingual

- Mistral 7B: 25.8 (#283)
- Mistral Medium 3.1: —

| Benchmark | Mistral 7B | Mistral Medium 3.1 |
|---|---|---|
| LMArena Non-English | 1012 | — |
| LMArena Chinese | 1009 | — |
| LMArena French | 1037 | — |
| LMArena German | 987 | — |
| LMArena Japanese | 878 | — |
| LMArena Russian | 1018 | — |
| LMArena Spanish | 1026 | — |

## Instruction Following

- Mistral 7B: 54.2 (#280)
- Mistral Medium 3.1: —

| Benchmark | Mistral 7B | Mistral Medium 3.1 |
|---|---|---|
| LMArena Instruction Following | 1060 | — |

## Long Context

- Mistral 7B: 32.2 (#271)
- Mistral Medium 3.1: —

| Benchmark | Mistral 7B | Mistral Medium 3.1 |
|---|---|---|
| LMArena Longer Query | 1060 | — |

## Writing & Preference

- Mistral 7B: 30.7 (#286)
- Mistral Medium 3.1: 55.5 (#145)

| Benchmark | Mistral 7B | Mistral Medium 3.1 |
|---|---|---|
| LMArena Text | 1090 | — |
| LMArena Creative Writing | 1068 | — |
| EQ-Bench Creative Writing | — | 1476 |
| LMArena Multi-Turn | 1062 | — |

## FAQ

### Is Mistral 7B better than Mistral Medium 3.1?

Mistral Medium 3.1 is the stronger model overall, scoring 31.9 to 23.0 on the Noometry Index. Mistral 7B costs 3.2× less per token, which makes it the better buy when Mistral Medium 3.1's lead doesn't matter for your workload.

### Which is cheaper, Mistral 7B or Mistral Medium 3.1?

Mistral 7B is cheaper. It lists at $0.25 per million input tokens and $0.25 per million output tokens; Mistral Medium 3.1 lists at $0.40 and $2.

### Which has the bigger context window?

Mistral Medium 3.1 does, with 131K tokens against 8K.

### How many benchmarks do Mistral 7B and Mistral Medium 3.1 share?

0 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Mistral Medium 3.1 has 3.