# Mistral Medium 3.5 vs Mistral Small

> Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 33.1 on the Noometry Index. Mistral Small costs 11× 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/mistral-medium-3-5-vs-mistral-small
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Mistral Medium 3.5 scores higher in 8 categories and Mistral Small in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Medium 3.5 leads 36.4 to 15.4.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- Mistral Medium 3.5 accepts more context: 262K tokens versus 256K.

## Snapshot

| | Mistral Medium 3.5 | Mistral Small |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 39.6 | 33.1 |
| Rank | 151 | 238 |
| Context | 262K | 256K |
| Input $/M | $1.50 | $0.15 |
| Output $/M | $7.50 | $0.60 |
| Weights | Open | Open |

## Coding

- Mistral Medium 3.5: 35.7 (#208)
- Mistral Small: 33.5 (#242)

| Benchmark | Mistral Medium 3.5 | Mistral Small |
|---|---|---|
| LMArena Coding | 1461 | 1363 |
| LMArena WebDev | 1263 | — |
| SciCode | — | 26.5% |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |

## Agentic & Tool Use

- Mistral Medium 3.5: —
- Mistral Small: 27.9 (#87)

| Benchmark | Mistral Medium 3.5 | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |

## Reasoning

- Mistral Medium 3.5: 16.6 (#290)
- Mistral Small: 19.3 (#238)

| Benchmark | Mistral Medium 3.5 | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 41.4% | 37.8% |
| LMArena Hard Prompts | 1436 | 1336 |
| NYT Connections (extended) | 12.9% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| Epoch Capabilities Index | 141.42 | — |
| LiveBench | — | 44% |

## Math

- Mistral Medium 3.5: 36.4 (#113)
- Mistral Small: 15.4 (#287)

| Benchmark | Mistral Medium 3.5 | Mistral Small |
|---|---|---|
| LMArena Math | 1432 | 1341 |
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |

## Knowledge

- Mistral Medium 3.5: 39.3 (#123)
- Mistral Small: 30.9 (#214)

| Benchmark | Mistral Medium 3.5 | Mistral Small |
|---|---|---|
| LMArena Expert | 1431 | 1293 |
| GPQA Diamond | — | 47.5% |
| Vectara Hallucination Rate | — | 5.1% |
| MMLU | — | 68.7% |

## Multimodal

- Mistral Medium 3.5: 37.6 (#64)
- Mistral Small: 32.9 (#91)

| Benchmark | Mistral Medium 3.5 | Mistral Small |
|---|---|---|
| LMArena Vision | 1222 | 1142 |

## Multilingual

- Mistral Medium 3.5: 52.1 (#93)
- Mistral Small: 45.7 (#164)

| Benchmark | Mistral Medium 3.5 | Mistral Small |
|---|---|---|
| LMArena Non-English | 1405 | 1315 |
| LMArena Chinese | 1443 | 1342 |
| LMArena French | 1448 | 1337 |
| LMArena German | 1453 | 1341 |
| LMArena Korean | 1387 | 1260 |
| LMArena Russian | 1396 | 1324 |
| LMArena Spanish | 1406 | 1346 |
| LMArena Japanese | — | 1275 |

## Instruction Following

- Mistral Medium 3.5: 74.7 (#87)
- Mistral Small: 66.6 (#204)

| Benchmark | Mistral Medium 3.5 | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1414 | 1310 |
| LiveBench Instruction Following | — | 63.7% |

## Long Context

- Mistral Medium 3.5: 43.2 (#101)
- Mistral Small: 40.4 (#151)

| Benchmark | Mistral Medium 3.5 | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1414 | 1327 |

## Writing & Preference

- Mistral Medium 3.5: 58.6 (#113)
- Mistral Small: 52.6 (#165)

| Benchmark | Mistral Medium 3.5 | Mistral Small |
|---|---|---|
| LMArena Text | 1421 | 1338 |
| LMArena Creative Writing | 1372 | 1304 |
| LMArena Multi-Turn | 1423 | 1344 |
| EQ-Bench 4 | 993 | — |
| LiveBench Language | — | 30.5% |

## FAQ

### Is Mistral Medium 3.5 better than Mistral Small?

Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 33.1 on the Noometry Index. Mistral Small costs 11× 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, Mistral Medium 3.5 or Mistral Small?

Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

### Is Mistral Medium 3.5 or Mistral Small better for coding?

Mistral Medium 3.5 scores higher on coding benchmarks: 35.7 versus 33.5 in the Noometry coding category.

### Which has the bigger context window?

Mistral Medium 3.5 does, with 262K tokens against 256K.

### How many benchmarks do Mistral Medium 3.5 and Mistral Small share?

18 benchmarks have published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and Mistral Small has 39.