# Gemma 2 27B vs Ministral 8B

> Gemma 2 27B is the stronger model overall, scoring 29.4 to 28.2 on the Noometry Index. Ministral 8B costs 4.3× less per token, which makes it the better buy when Gemma 2 27B's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemma-2-27b-vs-ministral-8b
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Gemma 2 27B scores higher in 5 categories and Ministral 8B in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Ministral 8B leads 25.7 to 10.7.
- The biggest single-benchmark swing is MATH Level 5: 27.9% for Gemma 2 27B and 14.9% for Ministral 8B.
- Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
- Ministral 8B accepts more context: 262K tokens versus 8K.

## Snapshot

| | Gemma 2 27B | Ministral 8B |
|---|---|---|
| Provider | Google | Mistral AI |
| Noometry Index | 29.4 | 28.2 |
| Rank | 312 | 325 |
| Context | 8K | 262K |
| Input $/M | $0.65 | $0.15 |
| Output $/M | $0.65 | $0.15 |
| Weights | Open | Open |

## Coding

- Gemma 2 27B: 34.1 (#246)
- Ministral 8B: 35.0 (#230)

| Benchmark | Gemma 2 27B | Ministral 8B |
|---|---|---|
| LMArena Coding | 1211 | 1202 |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |

## Agentic & Tool Use

- Gemma 2 27B: —
- Ministral 8B: 16.4 (#148)

| Benchmark | Gemma 2 27B | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |

## Reasoning

- Gemma 2 27B: 15.3 (#315)
- Ministral 8B: 18.4 (#281)

| Benchmark | Gemma 2 27B | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1191 |
| DTBench | 48% | 45.7% |
| LiveBench Reasoning | 28.1% | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| Epoch Capabilities Index | 122.08 | — |
| LiveBench | 38.2% | — |

## Math

- Gemma 2 27B: 10.7 (#311)
- Ministral 8B: 25.7 (#267)

| Benchmark | Gemma 2 27B | Ministral 8B |
|---|---|---|
| LMArena Math | 1212 | 1188 |
| MATH Level 5 | 27.9% | 14.9% |
| OTIS Mock AIME 2024-2025 | 1.4% | — |
| LiveBench Math | 26.5% | — |

## Knowledge

- Gemma 2 27B: 19.0 (#280)
- Ministral 8B: 12.6 (#297)

| Benchmark | Gemma 2 27B | Ministral 8B |
|---|---|---|
| GPQA Diamond | 36.5% | 27.1% |
| LMArena Expert | 1172 | 1170 |
| Confabulations | 27.1% | — |
| Vectara Hallucination Rate | — | 7.4% |
| MMLU | 75.7% | — |

## Multilingual

- Gemma 2 27B: 38.6 (#226)
- Ministral 8B: 35.1 (#247)

| Benchmark | Gemma 2 27B | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1217 | 1165 |
| LMArena Chinese | 1221 | 1193 |
| LMArena Russian | 1234 | 1195 |
| LMArena French | 1247 | — |
| LMArena German | 1209 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1174 | — |
| LMArena Spanish | 1228 | — |

## Instruction Following

- Gemma 2 27B: 60.5 (#249)
- Ministral 8B: 60.5 (#250)

| Benchmark | Gemma 2 27B | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1206 | 1161 |
| LiveBench Instruction Following | 58.1% | — |

## Long Context

- Gemma 2 27B: 37.3 (#218)
- Ministral 8B: 36.7 (#227)

| Benchmark | Gemma 2 27B | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1231 | 1212 |

## Writing & Preference

- Gemma 2 27B: 44.2 (#225)
- Ministral 8B: 39.6 (#246)

| Benchmark | Gemma 2 27B | Ministral 8B |
|---|---|---|
| LMArena Text | 1231 | 1191 |
| LMArena Creative Writing | 1241 | 1175 |
| LMArena Multi-Turn | 1224 | 1166 |
| LiveBench Language | 32.6% | — |

## FAQ

### Is Gemma 2 27B better than Ministral 8B?

Gemma 2 27B is the stronger model overall, scoring 29.4 to 28.2 on the Noometry Index. Ministral 8B costs 4.3× less per token, which makes it the better buy when Gemma 2 27B's lead doesn't matter for your workload.

### Which is cheaper, Gemma 2 27B or Ministral 8B?

Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Gemma 2 27B lists at $0.65 and $0.65.

### Is Gemma 2 27B or Ministral 8B better for coding?

They score almost the same on coding (34.1 vs 35.0); test both on your own repository before choosing.

### Which has the bigger context window?

Ministral 8B does, with 262K tokens against 8K.

### How many benchmarks do Gemma 2 27B and Ministral 8B share?

15 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Ministral 8B has 17.