# Gemma 3 12B vs Mistral Large

> Gemma 3 12B and Mistral Large score almost the same on the Noometry Index (32.1 vs 31.9), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/gemma-3-12b-vs-mistral-large
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Gemma 3 12B scores higher in 5 categories and Mistral Large in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3 12B leads 47.5 to 40.7.
- The biggest single-benchmark swing is SciCode: 17.4% for Gemma 3 12B and 36.2% for Mistral Large.
- Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $2 / $6 for Mistral Large.

## Snapshot

| | Gemma 3 12B | Mistral Large |
|---|---|---|
| Provider | Google | Mistral AI |
| Noometry Index | 32.1 | 31.9 |
| Rank | 262 | 263 |
| Context | 131K | 131K |
| Input $/M | $0.05 | $2 |
| Output $/M | $0.15 | $6 |
| Weights | Open | Open |

## Coding

- Gemma 3 12B: 31.7 (#280)
- Mistral Large: 34.3 (#240)

| Benchmark | Gemma 3 12B | Mistral Large |
|---|---|---|
| SciCode | 17.4% | 36.2% |
| LMArena Coding | 1281 | 1277 |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |

## Agentic & Tool Use

- Gemma 3 12B: 25.5 (#108)
- Mistral Large: 28.6 (#89)

| Benchmark | Gemma 3 12B | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | 38.4% |

## Reasoning

- Gemma 3 12B: 15.7 (#313)
- Mistral Large: 15.8 (#310)

| Benchmark | Gemma 3 12B | Mistral Large |
|---|---|---|
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1309 | 1257 |
| DTBench | 48.8% | 65.1% |
| LMCA | 4.5% | 16.7% |
| Epoch Capabilities Index | 123.5 | 128.52 |
| SimpleBench | — | 22.5% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 43.5% |
| LiveBench Data Analysis | — | 50.1% |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |

## Math

- Gemma 3 12B: 22.3 (#279)
- Mistral Large: 18.2 (#291)

| Benchmark | Gemma 3 12B | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | 8.5% |
| LMArena Math | 1307 | 1262 |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- Gemma 3 12B: 26.5 (#257)
- Mistral Large: 30.1 (#230)

| Benchmark | Gemma 3 12B | Mistral Large |
|---|---|---|
| GPQA Diamond | 39.5% | 51.3% |
| Vectara Hallucination Rate | 4.4% | 4.5% |
| LMArena Expert | 1248 | 1232 |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |

## Multimodal

- Gemma 3 12B: —
- Mistral Large: —

| Benchmark | Gemma 3 12B | Mistral Large |
|---|---|---|
| MindCube | 46.7% | — |

## Multilingual

- Gemma 3 12B: 45.7 (#165)
- Mistral Large: 40.0 (#219)

| Benchmark | Gemma 3 12B | Mistral Large |
|---|---|---|
| LMArena Non-English | 1318 | 1237 |
| LMArena German | 1370 | 1254 |
| LMArena Russian | 1335 | 1257 |
| LMArena Chinese | — | 1240 |
| LMArena French | — | 1325 |
| LMArena Japanese | — | 1188 |
| LMArena Korean | — | 1202 |
| LMArena Spanish | — | 1268 |

## Instruction Following

- Gemma 3 12B: 68.6 (#186)
- Mistral Large: 67.9 (#191)

| Benchmark | Gemma 3 12B | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1299 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |

## Long Context

- Gemma 3 12B: 40.0 (#162)
- Mistral Large: 38.3 (#199)

| Benchmark | Gemma 3 12B | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1317 | 1261 |

## Writing & Preference

- Gemma 3 12B: 47.5 (#209)
- Mistral Large: 40.7 (#242)

| Benchmark | Gemma 3 12B | Mistral Large |
|---|---|---|
| LMArena Text | 1334 | 1266 |
| LMArena Creative Writing | 1331 | 1243 |
| EQ-Bench Creative Writing | 1126 | 985 |
| LMArena Multi-Turn | 1334 | 1260 |
| Short-Story Creative Writing | — | 69% |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |

## FAQ

### Is Gemma 3 12B better than Mistral Large?

Gemma 3 12B and Mistral Large score almost the same on the Noometry Index (32.1 vs 31.9), so choose on price, context window or the category you care about most.

### Which is cheaper, Gemma 3 12B or Mistral Large?

Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Mistral Large lists at $2 and $6.

### Is Gemma 3 12B or Mistral Large better for coding?

Mistral Large scores higher on coding benchmarks: 34.3 versus 31.7 in the Noometry coding category.

### Which has the bigger context window?

Both accept 131K tokens.

### How many benchmarks do Gemma 3 12B and Mistral Large share?

22 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Mistral Large has 51.