# Granite 4.0 Micro vs Mistral Medium 3.5

> Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 28.8 on the Noometry Index. Granite 4.0 Micro costs 74× 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/granite-4-0-micro-vs-mistral-medium-3-5
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where Mistral Medium 3.5 leads 39.3 to 9.9.
- Granite 4.0 Micro is cheaper at $0.017 / $0.11 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 131K.

## Snapshot

| | Granite 4.0 Micro | Mistral Medium 3.5 |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 28.8 | 39.6 |
| Rank | 312 | 151 |
| Context | 131K | 262K |
| Input $/M | $0.017 | $1.50 |
| Output $/M | $0.11 | $7.50 |
| Weights | Open | Open |

## Coding

- Granite 4.0 Micro: —
- Mistral Medium 3.5: 35.7 (#208)

| Benchmark | Granite 4.0 Micro | Mistral Medium 3.5 |
|---|---|---|
| LMArena WebDev | — | 1263 |
| LMArena Coding | — | 1461 |

## Reasoning

- Granite 4.0 Micro: 18.5 (#261)
- Mistral Medium 3.5: 16.6 (#290)

| Benchmark | Granite 4.0 Micro | Mistral Medium 3.5 |
|---|---|---|
| Kagi LLM Benchmark | — | 41.4% |
| NYT Connections (extended) | — | 12.9% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | — | 1436 |
| Epoch Capabilities Index | — | 141.42 |

## Math

- Granite 4.0 Micro: 11.2 (#301)
- Mistral Medium 3.5: 36.4 (#113)

| Benchmark | Granite 4.0 Micro | Mistral Medium 3.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.8% | — |
| Omni-MATH | 20.9% | — |
| LMArena Math | — | 1432 |

## Knowledge

- Granite 4.0 Micro: 9.9 (#299)
- Mistral Medium 3.5: 39.3 (#123)

| Benchmark | Granite 4.0 Micro | Mistral Medium 3.5 |
|---|---|---|
| GPQA Diamond | 28.3% | — |
| MMLU-Pro | 39.5% | — |
| GPQA (HELM) | 30.7% | — |
| LMArena Expert | — | 1431 |

## Multimodal

- Granite 4.0 Micro: —
- Mistral Medium 3.5: 37.6 (#64)

| Benchmark | Granite 4.0 Micro | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | — | 1222 |

## Multilingual

- Granite 4.0 Micro: —
- Mistral Medium 3.5: 52.1 (#93)

| Benchmark | Granite 4.0 Micro | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | — | 1405 |
| LMArena Chinese | — | 1443 |
| LMArena French | — | 1448 |
| LMArena German | — | 1453 |
| LMArena Korean | — | 1387 |
| LMArena Russian | — | 1396 |
| LMArena Spanish | — | 1406 |

## Instruction Following

- Granite 4.0 Micro: 70.0 (#164)
- Mistral Medium 3.5: 74.7 (#87)

| Benchmark | Granite 4.0 Micro | Mistral Medium 3.5 |
|---|---|---|
| IFEval | 84.9% | — |
| LMArena Instruction Following | — | 1414 |

## Long Context

- Granite 4.0 Micro: —
- Mistral Medium 3.5: 43.2 (#101)

| Benchmark | Granite 4.0 Micro | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | — | 1414 |

## Writing & Preference

- Granite 4.0 Micro: 46.7 (#212)
- Mistral Medium 3.5: 58.6 (#113)

| Benchmark | Granite 4.0 Micro | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | — | 1421 |
| LMArena Creative Writing | — | 1372 |
| WildBench | 67% | — |
| EQ-Bench 4 | — | 993 |
| LMArena Multi-Turn | — | 1423 |

## FAQ

### Is Granite 4.0 Micro better than Mistral Medium 3.5?

Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 28.8 on the Noometry Index. Granite 4.0 Micro costs 74× 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, Granite 4.0 Micro or Mistral Medium 3.5?

Granite 4.0 Micro is cheaper. It lists at $0.017 per million input tokens and $0.11 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

### Which has the bigger context window?

Mistral Medium 3.5 does, with 262K tokens against 131K.

### How many benchmarks do Granite 4.0 Micro and Mistral Medium 3.5 share?

0 benchmarks have published results for both models. Granite 4.0 Micro has 8 scored results on Noometry and Mistral Medium 3.5 has 22.