# Gemma 2 27B vs Mistral Medium

> Mistral Medium is the stronger model overall, scoring 36.3 to 29.4 on the Noometry Index. Gemma 2 27B costs 4.6× 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/gemma-2-27b-vs-mistral-medium
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and Mistral Medium in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Medium leads 28.1 to 10.7.
- The biggest single-benchmark swing is MATH Level 5: 27.9% for Gemma 2 27B and 81.6% for Mistral Medium.
- Gemma 2 27B is cheaper at $0.65 / $0.65 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 8K.

## Snapshot

| | Gemma 2 27B | Mistral Medium |
|---|---|---|
| Provider | Google | Mistral AI |
| Noometry Index | 29.4 | 36.3 |
| Rank | 312 | 218 |
| Context | 8K | 262K |
| Input $/M | $0.65 | $1.50 |
| Output $/M | $0.65 | $7.50 |
| Weights | Open | Open |

## Coding

- Gemma 2 27B: 34.1 (#246)
- Mistral Medium: 34.2 (#243)

| Benchmark | Gemma 2 27B | Mistral Medium |
|---|---|---|
| LMArena Coding | 1211 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | — | 763.98 |

## Agentic & Tool Use

- Gemma 2 27B: —
- Mistral Medium: 28.3 (#90)

| Benchmark | Gemma 2 27B | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |

## Reasoning

- Gemma 2 27B: 15.3 (#315)
- Mistral Medium: 24.0 (#167)

| Benchmark | Gemma 2 27B | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1426 |
| DTBench | 48% | 75.5% |
| LMCA | 7.1% | 26.1% |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| LiveBench Reasoning | 28.1% | — |
| LiveBench Data Analysis | 47.9% | — |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 122.08 | — |
| LiveBench | 38.2% | — |

## Math

- Gemma 2 27B: 10.7 (#311)
- Mistral Medium: 28.1 (#245)

| Benchmark | Gemma 2 27B | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.4% | 32.2% |
| LMArena Math | 1212 | 1408 |
| MATH Level 5 | 27.9% | 81.6% |
| ProofBench | — | 9% |
| LiveBench Math | 26.5% | — |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- Gemma 2 27B: 19.0 (#280)
- Mistral Medium: 25.0 (#265)

| Benchmark | Gemma 2 27B | Mistral Medium |
|---|---|---|
| GPQA Diamond | 36.5% | 59.5% |
| LMArena Expert | 1172 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| Confabulations | 27.1% | — |
| Vectara Hallucination Rate | — | 22.7% |
| MMLU | 75.7% | — |

## Multimodal

- Gemma 2 27B: —
- Mistral Medium: 35.3 (#88)

| Benchmark | Gemma 2 27B | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |

## Multilingual

- Gemma 2 27B: 38.6 (#226)
- Mistral Medium: 52.1 (#91)

| Benchmark | Gemma 2 27B | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1217 | 1408 |
| LMArena Chinese | 1221 | 1447 |
| LMArena French | 1247 | 1459 |
| LMArena German | 1209 | 1432 |
| LMArena Japanese | 1175 | 1378 |
| LMArena Korean | 1174 | 1380 |
| LMArena Russian | 1234 | 1411 |
| LMArena Spanish | 1228 | 1433 |

## Instruction Following

- Gemma 2 27B: 60.5 (#249)
- Mistral Medium: 73.7 (#116)

| Benchmark | Gemma 2 27B | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1206 | 1398 |
| LiveBench Instruction Following | 58.1% | — |

## Long Context

- Gemma 2 27B: 37.3 (#218)
- Mistral Medium: 42.9 (#114)

| Benchmark | Gemma 2 27B | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1231 | 1406 |

## Writing & Preference

- Gemma 2 27B: 44.2 (#225)
- Mistral Medium: 60.0 (#103)

| Benchmark | Gemma 2 27B | Mistral Medium |
|---|---|---|
| LMArena Text | 1231 | 1424 |
| LMArena Creative Writing | 1241 | 1391 |
| LMArena Multi-Turn | 1224 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| LiveBench Language | 32.6% | — |

## FAQ

### Is Gemma 2 27B better than Mistral Medium?

Mistral Medium is the stronger model overall, scoring 36.3 to 29.4 on the Noometry Index. Gemma 2 27B costs 4.6× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.

### Which is cheaper, Gemma 2 27B or Mistral Medium?

Gemma 2 27B is cheaper. It lists at $0.65 per million input tokens and $0.65 per million output tokens; Mistral Medium lists at $1.50 and $7.50.

### Is Gemma 2 27B or Mistral Medium better for coding?

They score almost the same on coding (34.1 vs 34.2); test both on your own repository before choosing.

### Which has the bigger context window?

Mistral Medium does, with 262K tokens against 8K.

### How many benchmarks do Gemma 2 27B and Mistral Medium share?

22 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Mistral Medium has 36.