Model comparison
Gemma 2B vs Mistral
Gemma 2B and Mistral score almost the same on the Noometry Index (29.6 vs 29.9), so choose on price, context window or the category you care about most.
Last verified . 11 shared benchmarks.
Google
Mistral AISummary
- They share 11 benchmarks with published results for both. Gemma 2B scores higher in 1 category and Mistral in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral leads 37.0 to 24.0.
- Gemma 2B has downloadable open weights; the other is API-only.
Side by side
| Gemma 2B | Mistral | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 29.6 | 29.9 |
| Released | 2024-02-21 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 23 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Gemma 2B: 29.4 (#305), Mistral: 33.8 (#250)
| Benchmark | Gemma 2B | Mistral |
|---|---|---|
| LMArena Coding | 1010 | 1162 |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Reasoning Mistral leads
Gemma 2B: 18.8 (#275), Mistral: 22.2 (#200)
| Benchmark | Gemma 2B | Mistral |
|---|---|---|
| LMArena Hard Prompts | 989 | 1149 |
| BIG-Bench Hard | 35.2% | — |
| Epoch Capabilities Index | 94.2 | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Gemma 2B leads
Gemma 2B: 30.0 (#239), Mistral: 22.3 (#278)
| Benchmark | Gemma 2B | Mistral |
|---|---|---|
| LMArena Math | 1009 | 1180 |
| Omni-MATH | — | 7.2% |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Mistral: 16.6 (#288)
| Benchmark | Gemma 2B | Mistral |
|---|---|---|
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
| LMArena Expert | — | 1125 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual Mistral leads
Gemma 2B: 23.0 (#294), Mistral: 32.8 (#254)
| Benchmark | Gemma 2B | Mistral |
|---|---|---|
| LMArena Non-English | 958 | 1129 |
| LMArena Chinese | 986 | 1109 |
| LMArena Russian | 937 | 1168 |
| LMArena French | — | 1180 |
| LMArena German | — | 1155 |
| LMArena Japanese | — | 1013 |
| LMArena Korean | — | 1032 |
| LMArena Spanish | — | 1143 |
Instruction Following Mistral leads
Gemma 2B: 48.5 (#302), Mistral: 52.6 (#288)
| Benchmark | Gemma 2B | Mistral |
|---|---|---|
| LMArena Instruction Following | 970 | 1152 |
| IFEval | — | 56.8% |
Long Context Mistral leads
Gemma 2B: 29.9 (#291), Mistral: 35.0 (#245)
| Benchmark | Gemma 2B | Mistral |
|---|---|---|
| LMArena Longer Query | 981 | 1153 |
Writing & Preference Mistral leads
Gemma 2B: 24.0 (#308), Mistral: 37.0 (#260)
| Benchmark | Gemma 2B | Mistral |
|---|---|---|
| LMArena Text | 1002 | 1165 |
| LMArena Creative Writing | 987 | 1158 |
| LMArena Multi-Turn | 945 | 1147 |
| WildBench | — | 66% |
Frequently asked questions
Is Gemma 2B better than Mistral?
Gemma 2B and Mistral score almost the same on the Noometry Index (29.6 vs 29.9), so choose on price, context window or the category you care about most.
Is Gemma 2B or Mistral better for coding?
Mistral scores higher on coding benchmarks: 33.8 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2B and Mistral share?
11 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Mistral has 22.