Model comparison
Gemma 3 12B vs Mistral
Gemma 3 12B is the stronger model overall, scoring 31.8 to 29.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
Google
Mistral AISummary
- They share 12 benchmarks with published results for both. Gemma 3 12B scores higher in 6 categories and Mistral in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Gemma 3 12B leads 68.8 to 52.9.
- Gemma 3 12B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 12B | Mistral | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 31.8 | 29.4 |
| Released | 2025-03-12 | — |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 24 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Gemma 3 12B: 31.2 (#276), Mistral: 33.2 (#249)
| Benchmark | Gemma 3 12B | Mistral |
|---|---|---|
| LMArena Coding | 1281 | 1162 |
| SciCode | 17.4% | — |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.3 (#101), Mistral: —
| Benchmark | Gemma 3 12B | Mistral |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning Mistral leads
Gemma 3 12B: 15.2 (#307), Mistral: 21.3 (#199)
| Benchmark | Gemma 3 12B | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1149 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.49 | — |
Math Too close to call
Gemma 3 12B: 21.0 (#273), Mistral: 20.5 (#275)
| Benchmark | Gemma 3 12B | Mistral |
|---|---|---|
| LMArena Math | 1307 | 1180 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
| Omni-MATH | — | 7.2% |
Knowledge Gemma 3 12B leads
Gemma 3 12B: 26.5 (#250), Mistral: 16.3 (#283)
| Benchmark | Gemma 3 12B | Mistral |
|---|---|---|
| LMArena Expert | 1248 | 1125 |
| GPQA Diamond | 39.5% | — |
| MMLU-Pro | — | 27.7% |
| Vectara Hallucination Rate | 4.4% | — |
| GPQA (HELM) | — | 30.3% |
Multimodal Not comparable
Gemma 3 12B: —, Mistral: —
| Benchmark | Gemma 3 12B | Mistral |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Gemma 3 12B leads
Gemma 3 12B: 45.9 (#160), Mistral: 33.0 (#249)
| Benchmark | Gemma 3 12B | Mistral |
|---|---|---|
| LMArena Non-English | 1318 | 1129 |
| LMArena German | 1370 | 1155 |
| LMArena Russian | 1335 | 1168 |
| LMArena Chinese | — | 1109 |
| LMArena French | — | 1179 |
| LMArena Japanese | — | 1012 |
| LMArena Korean | — | 1032 |
| LMArena Spanish | — | 1143 |
Instruction Following Gemma 3 12B leads
Gemma 3 12B: 68.8 (#179), Mistral: 52.9 (#283)
| Benchmark | Gemma 3 12B | Mistral |
|---|---|---|
| LMArena Instruction Following | 1299 | 1152 |
| IFEval | — | 56.8% |
Long Context Gemma 3 12B leads
Gemma 3 12B: 40.0 (#157), Mistral: 35.0 (#240)
| Benchmark | Gemma 3 12B | Mistral |
|---|---|---|
| LMArena Longer Query | 1317 | 1154 |
Writing & Preference Gemma 3 12B leads
Gemma 3 12B: 47.7 (#205), Mistral: 37.2 (#255)
| Benchmark | Gemma 3 12B | Mistral |
|---|---|---|
| LMArena Text | 1334 | 1165 |
| LMArena Creative Writing | 1331 | 1158 |
| LMArena Multi-Turn | 1334 | 1147 |
| EQ-Bench Creative Writing | 1126 | — |
| WildBench | — | 66% |
Frequently asked questions
Is Gemma 3 12B better than Mistral?
Gemma 3 12B is the stronger model overall, scoring 31.8 to 29.4 on the Noometry Index.
Is Gemma 3 12B or Mistral better for coding?
Mistral scores higher on coding benchmarks: 33.2 versus 31.2 in the Noometry coding category.
How many benchmarks do Gemma 3 12B and Mistral share?
12 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Mistral has 22.