Model comparison
Gemma 2B vs Mistral 7B
Gemma 2B is the stronger model overall, scoring 29.6 to 23.0 on the Noometry Index.
Last verified . 23 shared benchmarks.
Google
Mistral AISummary
- They share 23 benchmarks with published results for both. Gemma 2B scores higher in 3 categories and Mistral 7B in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 2B leads 30.0 to 8.1.
Side by side
| Gemma 2B | Mistral 7B | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 29.6 | 23.0 |
| Released | 2024-02-21 | 2023-09-27 |
| Weights | Open | Open |
| Context window | — | 8K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.25 |
| Results tracked | 23 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2B leads
Gemma 2B: 29.4 (#305), Mistral 7B: 26.4 (#326)
| Benchmark | Gemma 2B | Mistral 7B |
|---|---|---|
| LMArena Coding | 1010 | 1082 |
| HumanEval+ | 20.7% | 36% |
| MBPP+ | 34.1% | 42.1% |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
Reasoning Gemma 2B leads
Gemma 2B: 18.8 (#275), Mistral 7B: 13.1 (#336)
| Benchmark | Gemma 2B | Mistral 7B |
|---|---|---|
| LMArena Hard Prompts | 989 | 1067 |
| BIG-Bench Hard | 35.2% | 56.1% |
| Epoch Capabilities Index | 94.2 | 112.21 |
| HellaSwag | 71.4% | 81% |
| PIQA | 77.3% | 83% |
| WinoGrande | 65.4% | 75.3% |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.5% |
| Adversarial NLI | — | 47.1% |
Math Gemma 2B leads
Gemma 2B: 30.0 (#239), Mistral 7B: 8.1 (#325)
| Benchmark | Gemma 2B | Mistral 7B |
|---|---|---|
| LMArena Math | 1009 | 1085 |
| GSM8K | 17.7% | 54.4% |
| OTIS Mock AIME 2024-2025 | — | 0.3% |
| MATH Level 5 | — | 3.7% |
Knowledge Not comparable
Gemma 2B: —, Mistral 7B: 7.4 (#311)
| Benchmark | Gemma 2B | Mistral 7B |
|---|---|---|
| ARC (AI2) Challenge | 42.1% | 78.6% |
| BoolQ | 69.4% | 87.4% |
| MMLU | 42.3% | 62.5% |
| TriviaQA | 53.2% | 75.2% |
| GPQA Diamond | — | 15.2% |
| LMArena Expert | — | 1036 |
| OpenBookQA | — | 79.8% |
Multilingual Mistral 7B leads
Gemma 2B: 23.0 (#294), Mistral 7B: 25.8 (#283)
| Benchmark | Gemma 2B | Mistral 7B |
|---|---|---|
| LMArena Non-English | 958 | 1012 |
| LMArena Chinese | 986 | 1009 |
| LMArena Russian | 937 | 1018 |
| LMArena French | — | 1037 |
| LMArena German | — | 987 |
| LMArena Japanese | — | 878 |
| LMArena Spanish | — | 1026 |
Instruction Following Mistral 7B leads
Gemma 2B: 48.5 (#302), Mistral 7B: 54.2 (#280)
| Benchmark | Gemma 2B | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 970 | 1060 |
Long Context Mistral 7B leads
Gemma 2B: 29.9 (#291), Mistral 7B: 32.2 (#271)
| Benchmark | Gemma 2B | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 981 | 1060 |
Writing & Preference Mistral 7B leads
Gemma 2B: 24.0 (#308), Mistral 7B: 30.7 (#286)
| Benchmark | Gemma 2B | Mistral 7B |
|---|---|---|
| LMArena Text | 1002 | 1090 |
| LMArena Creative Writing | 987 | 1068 |
| LMArena Multi-Turn | 945 | 1062 |
Frequently asked questions
Is Gemma 2B better than Mistral 7B?
Gemma 2B is the stronger model overall, scoring 29.6 to 23.0 on the Noometry Index.
Is Gemma 2B or Mistral 7B better for coding?
Gemma 2B scores higher on coding benchmarks: 29.4 versus 26.4 in the Noometry coding category.
How many benchmarks do Gemma 2B and Mistral 7B share?
23 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Mistral 7B has 37.