Model comparison
Gemma 2 9B vs Ministral 3B
Gemma 2 9B and Ministral 3B score almost the same on the Noometry Index (25.9 vs 26.2), so choose on price, context window or the category you care about most.
Last verified . 3 shared benchmarks.
Google
Mistral AISummary
- They share 3 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Ministral 3B in 3 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where Ministral 3B leads 26.6 to 9.9.
- The biggest single-benchmark swing is MATH Level 5: 21% for Gemma 2 9B and 14.4% for Ministral 3B.
Side by side
| Gemma 2 9B | Ministral 3B | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 25.9 | 26.2 |
| Released | 2024-06-24 | 2024-10-01 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.10 |
| Results tracked | 35 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemma 2 9B: 29.4 (#304), Ministral 3B: —
| Benchmark | Gemma 2 9B | Ministral 3B |
|---|---|---|
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| LMArena Coding | 1173 | — |
| BigCodeBench Complete | 40.6% | — |
Reasoning Ministral 3B leads
Gemma 2 9B: 15.9 (#309), Ministral 3B: 18.4 (#282)
| Benchmark | Gemma 2 9B | Ministral 3B |
|---|---|---|
| Epoch Capabilities Index | 119.83 | 118.1 |
| LiveBench Reasoning | 15.2% | — |
| LMArena Hard Prompts | 1171 | — |
| DTBench | — | 51.7% |
| LiveBench Data Analysis | 36.4% | — |
| LMCA | — | 5.5% |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math Ministral 3B leads
Gemma 2 9B: 9.9 (#318), Ministral 3B: 26.6 (#258)
| Benchmark | Gemma 2 9B | Ministral 3B |
|---|---|---|
| MATH Level 5 | 21% | 14.4% |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| LiveBench Math | 19.8% | — |
| LMArena Math | 1183 | — |
| GSM8K | 84.9% | — |
Knowledge Too close to call
Gemma 2 9B: 9.7 (#305), Ministral 3B: 10.4 (#302)
| Benchmark | Gemma 2 9B | Ministral 3B |
|---|---|---|
| GPQA Diamond | 27.5% | 25.3% |
| Vectara Hallucination Rate | — | 7.3% |
| LMArena Expert | 1147 | — |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multilingual Not comparable
Gemma 2 9B: 36.6 (#238), Ministral 3B: —
| Benchmark | Gemma 2 9B | Ministral 3B |
|---|---|---|
| LMArena Non-English | 1188 | — |
| LMArena Chinese | 1185 | — |
| LMArena French | 1190 | — |
| LMArena German | 1186 | — |
| LMArena Japanese | 1144 | — |
| LMArena Korean | 1137 | — |
| LMArena Russian | 1200 | — |
| LMArena Spanish | 1200 | — |
Instruction Following Not comparable
Gemma 2 9B: 57.6 (#269), Ministral 3B: —
| Benchmark | Gemma 2 9B | Ministral 3B |
|---|---|---|
| LiveBench Instruction Following | 52.6% | — |
| LMArena Instruction Following | 1178 | — |
Long Context Not comparable
Gemma 2 9B: 36.3 (#233), Ministral 3B: —
| Benchmark | Gemma 2 9B | Ministral 3B |
|---|---|---|
| LMArena Longer Query | 1197 | — |
Writing & Preference Not comparable
Gemma 2 9B: 32.1 (#281), Ministral 3B: —
| Benchmark | Gemma 2 9B | Ministral 3B |
|---|---|---|
| LMArena Text | 1207 | — |
| LMArena Creative Writing | 1206 | — |
| EQ-Bench Creative Writing | 841 | — |
| LMArena Multi-Turn | 1193 | — |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Ministral 3B?
Gemma 2 9B and Ministral 3B score almost the same on the Noometry Index (25.9 vs 26.2), so choose on price, context window or the category you care about most.
How many benchmarks do Gemma 2 9B and Ministral 3B share?
3 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Ministral 3B has 6.