# Granite 4.0 Micro vs Mistral Medium

> Mistral Medium is the stronger model overall, scoring 36.3 to 29.0 on the Noometry Index. Granite 4.0 Micro costs 74× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/granite-4-0-micro-vs-mistral-medium
- Last updated: 2026-10-11
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Granite 4.0 Micro scores higher in 0 categories and Mistral Medium in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Medium leads 28.1 to 12.0.
- The biggest single-benchmark swing is GPQA Diamond: 28.3% for Granite 4.0 Micro and 59.5% for Mistral Medium.
- Granite 4.0 Micro is cheaper at $0.017 / $0.11 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 131K.

## Snapshot

| | Granite 4.0 Micro | Mistral Medium |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 29.0 | 36.3 |
| Rank | 318 | 218 |
| 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: 34.2 (#243)

| Benchmark | Granite 4.0 Micro | Mistral Medium |
|---|---|---|
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| LMArena Coding | — | 1434 |
| ALE-Bench | — | 763.98 |

## Agentic & Tool Use

- Granite 4.0 Micro: —
- Mistral Medium: 28.3 (#90)

| Benchmark | Granite 4.0 Micro | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |

## Reasoning

- Granite 4.0 Micro: 19.2 (#265)
- Mistral Medium: 24.0 (#167)

| Benchmark | Granite 4.0 Micro | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | — | 1426 |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |

## Math

- Granite 4.0 Micro: 12.0 (#307)
- Mistral Medium: 28.1 (#245)

| Benchmark | Granite 4.0 Micro | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.8% | 32.2% |
| ProofBench | — | 9% |
| Omni-MATH | 20.9% | — |
| LMArena Math | — | 1408 |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- Granite 4.0 Micro: 9.9 (#304)
- Mistral Medium: 25.0 (#265)

| Benchmark | Granite 4.0 Micro | Mistral Medium |
|---|---|---|
| GPQA Diamond | 28.3% | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| MMLU-Pro | 39.5% | — |
| Vectara Hallucination Rate | — | 22.7% |
| GPQA (HELM) | 30.7% | — |
| LMArena Expert | — | 1408 |

## Multimodal

- Granite 4.0 Micro: —
- Mistral Medium: 35.3 (#88)

| Benchmark | Granite 4.0 Micro | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |

## Multilingual

- Granite 4.0 Micro: —
- Mistral Medium: 52.1 (#91)

| Benchmark | Granite 4.0 Micro | Mistral Medium |
|---|---|---|
| LMArena Non-English | — | 1408 |
| LMArena Chinese | — | 1447 |
| LMArena French | — | 1459 |
| LMArena German | — | 1432 |
| LMArena Japanese | — | 1378 |
| LMArena Korean | — | 1380 |
| LMArena Russian | — | 1411 |
| LMArena Spanish | — | 1433 |

## Instruction Following

- Granite 4.0 Micro: 69.9 (#169)
- Mistral Medium: 73.7 (#116)

| Benchmark | Granite 4.0 Micro | Mistral Medium |
|---|---|---|
| IFEval | 84.9% | — |
| LMArena Instruction Following | — | 1398 |

## Long Context

- Granite 4.0 Micro: —
- Mistral Medium: 42.9 (#114)

| Benchmark | Granite 4.0 Micro | Mistral Medium |
|---|---|---|
| LMArena Longer Query | — | 1406 |

## Writing & Preference

- Granite 4.0 Micro: 46.7 (#216)
- Mistral Medium: 60.0 (#103)

| Benchmark | Granite 4.0 Micro | Mistral Medium |
|---|---|---|
| LMArena Text | — | 1424 |
| LMArena Creative Writing | — | 1391 |
| Short-Story Creative Writing | — | 77.3% |
| WildBench | 67% | — |
| LMArena Multi-Turn | — | 1418 |

## FAQ

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

Mistral Medium is the stronger model overall, scoring 36.3 to 29.0 on the Noometry Index. Granite 4.0 Micro costs 74× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.

### Which is cheaper, Granite 4.0 Micro or Mistral Medium?

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

### Which has the bigger context window?

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

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

2 benchmarks have published results for both models. Granite 4.0 Micro has 8 scored results on Noometry and Mistral Medium has 36.