Model comparison
Gemma 7B vs Ministral 8B
Gemma 7B is the stronger model overall, scoring 30.0 to 28.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Google
Mistral AISummary
- They share 12 benchmarks with published results for both. Gemma 7B scores higher in 3 categories and Ministral 8B in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 7B leads 27.3 to 12.6.
Side by side
| Gemma 7B | Ministral 8B | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 30.0 | 28.2 |
| Released | 2024-02-21 | 2024-10-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 27 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ministral 8B leads
Gemma 7B: 30.5 (#294), Ministral 8B: 35.0 (#230)
| Benchmark | Gemma 7B | Ministral 8B |
|---|---|---|
| LMArena Coding | 1048 | 1202 |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |
Agentic & Tool Use Not comparable
Gemma 7B: —, Ministral 8B: 16.4 (#148)
| Benchmark | Gemma 7B | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
Reasoning Gemma 7B leads
Gemma 7B: 19.9 (#249), Ministral 8B: 18.4 (#281)
| Benchmark | Gemma 7B | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1191 |
| DTBench | — | 45.7% |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| Epoch Capabilities Index | 111.99 | — |
| HellaSwag | 82.2% | — |
| PIQA | 81.2% | — |
| WinoGrande | 79% | — |
Math Gemma 7B leads
Gemma 7B: 31.2 (#228), Ministral 8B: 25.7 (#267)
| Benchmark | Gemma 7B | Ministral 8B |
|---|---|---|
| LMArena Math | 1066 | 1188 |
| MATH Level 5 | — | 14.9% |
| GSM8K | 46.4% | — |
Knowledge Gemma 7B leads
Gemma 7B: 27.3 (#252), Ministral 8B: 12.6 (#297)
| Benchmark | Gemma 7B | Ministral 8B |
|---|---|---|
| LMArena Expert | 1001 | 1170 |
| GPQA Diamond | — | 27.1% |
| Vectara Hallucination Rate | — | 7.4% |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| MMLU | 66.1% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |
Multilingual Ministral 8B leads
Gemma 7B: 25.1 (#287), Ministral 8B: 35.1 (#247)
| Benchmark | Gemma 7B | Ministral 8B |
|---|---|---|
| LMArena Non-English | 999 | 1165 |
| LMArena Chinese | 1035 | 1193 |
| LMArena Russian | 993 | 1195 |
| LMArena French | 1025 | — |
Instruction Following Ministral 8B leads
Gemma 7B: 51.5 (#295), Ministral 8B: 60.5 (#250)
| Benchmark | Gemma 7B | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1017 | 1161 |
Long Context Ministral 8B leads
Gemma 7B: 31.1 (#282), Ministral 8B: 36.7 (#227)
| Benchmark | Gemma 7B | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1022 | 1212 |
Writing & Preference Ministral 8B leads
Gemma 7B: 27.1 (#302), Ministral 8B: 39.6 (#246)
| Benchmark | Gemma 7B | Ministral 8B |
|---|---|---|
| LMArena Text | 1056 | 1191 |
| LMArena Creative Writing | 1024 | 1175 |
| LMArena Multi-Turn | 963 | 1166 |
Frequently asked questions
Is Gemma 7B better than Ministral 8B?
Gemma 7B is the stronger model overall, scoring 30.0 to 28.2 on the Noometry Index.
Is Gemma 7B or Ministral 8B better for coding?
Ministral 8B scores higher on coding benchmarks: 35.0 versus 30.5 in the Noometry coding category.
How many benchmarks do Gemma 7B and Ministral 8B share?
12 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Ministral 8B has 17.