Model comparison
Gemma 7B vs Mistral 7B
Gemma 7B is the stronger model overall, scoring 30.0 to 23.0 on the Noometry Index.
Last verified . 27 shared benchmarks.
Google
Mistral AISummary
- They share 27 benchmarks with published results for both. Gemma 7B scores higher in 4 categories and Mistral 7B in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 7B leads 31.2 to 8.1.
Side by side
| Gemma 7B | Mistral 7B | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 30.0 | 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 | 27 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 7B leads
Gemma 7B: 30.5 (#294), Mistral 7B: 26.4 (#326)
| Benchmark | Gemma 7B | Mistral 7B |
|---|---|---|
| LMArena Coding | 1048 | 1082 |
| HumanEval+ | 28.7% | 36% |
| MBPP+ | 43.4% | 42.1% |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
Reasoning Gemma 7B leads
Gemma 7B: 19.9 (#249), Mistral 7B: 13.1 (#336)
| Benchmark | Gemma 7B | Mistral 7B |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1067 |
| Adversarial NLI | 48.7% | 47.1% |
| BIG-Bench Hard | 55.1% | 56.1% |
| Epoch Capabilities Index | 111.99 | 112.21 |
| HellaSwag | 82.2% | 81% |
| PIQA | 81.2% | 83% |
| WinoGrande | 79% | 75.3% |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.5% |
Math Gemma 7B leads
Gemma 7B: 31.2 (#228), Mistral 7B: 8.1 (#325)
| Benchmark | Gemma 7B | Mistral 7B |
|---|---|---|
| LMArena Math | 1066 | 1085 |
| GSM8K | 46.4% | 54.4% |
| OTIS Mock AIME 2024-2025 | — | 0.3% |
| MATH Level 5 | — | 3.7% |
Knowledge Gemma 7B leads
Gemma 7B: 27.3 (#252), Mistral 7B: 7.4 (#311)
| Benchmark | Gemma 7B | Mistral 7B |
|---|---|---|
| LMArena Expert | 1001 | 1036 |
| ARC (AI2) Challenge | 78.3% | 78.6% |
| BoolQ | 83.2% | 87.4% |
| MMLU | 66.1% | 62.5% |
| OpenBookQA | 78.6% | 79.8% |
| TriviaQA | 72.3% | 75.2% |
| GPQA Diamond | — | 15.2% |
Multilingual Too close to call
Gemma 7B: 25.1 (#287), Mistral 7B: 25.8 (#283)
| Benchmark | Gemma 7B | Mistral 7B |
|---|---|---|
| LMArena Non-English | 999 | 1012 |
| LMArena Chinese | 1035 | 1009 |
| LMArena French | 1025 | 1037 |
| LMArena Russian | 993 | 1018 |
| LMArena German | — | 987 |
| LMArena Japanese | — | 878 |
| LMArena Spanish | — | 1026 |
Instruction Following Mistral 7B leads
Gemma 7B: 51.5 (#295), Mistral 7B: 54.2 (#280)
| Benchmark | Gemma 7B | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1017 | 1060 |
Long Context Mistral 7B leads
Gemma 7B: 31.1 (#282), Mistral 7B: 32.2 (#271)
| Benchmark | Gemma 7B | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1022 | 1060 |
Writing & Preference Mistral 7B leads
Gemma 7B: 27.1 (#302), Mistral 7B: 30.7 (#286)
| Benchmark | Gemma 7B | Mistral 7B |
|---|---|---|
| LMArena Text | 1056 | 1090 |
| LMArena Creative Writing | 1024 | 1068 |
| LMArena Multi-Turn | 963 | 1062 |
Frequently asked questions
Is Gemma 7B better than Mistral 7B?
Gemma 7B is the stronger model overall, scoring 30.0 to 23.0 on the Noometry Index.
Is Gemma 7B or Mistral 7B better for coding?
Gemma 7B scores higher on coding benchmarks: 30.5 versus 26.4 in the Noometry coding category.
How many benchmarks do Gemma 7B and Mistral 7B share?
27 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Mistral 7B has 37.