Model comparison
Gemma 2 9B vs Ministral 8B
Ministral 8B is the stronger model overall, scoring 28.2 to 25.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
Google
Mistral AISummary
- They share 14 benchmarks with published results for both. Gemma 2 9B scores higher in 1 category and Ministral 8B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Ministral 8B leads 25.7 to 9.9.
- The biggest single-benchmark swing is MATH Level 5: 21% for Gemma 2 9B and 14.9% for Ministral 8B.
Side by side
| Gemma 2 9B | Ministral 8B | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 25.9 | 28.2 |
| Released | 2024-06-24 | 2024-10-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 35 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ministral 8B leads
Gemma 2 9B: 29.4 (#304), Ministral 8B: 35.0 (#230)
| Benchmark | Gemma 2 9B | Ministral 8B |
|---|---|---|
| LMArena Coding | 1173 | 1202 |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
Agentic & Tool Use Not comparable
Gemma 2 9B: —, Ministral 8B: 16.4 (#148)
| Benchmark | Gemma 2 9B | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
Reasoning Ministral 8B leads
Gemma 2 9B: 15.9 (#309), Ministral 8B: 18.4 (#281)
| Benchmark | Gemma 2 9B | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1191 |
| LiveBench Reasoning | 15.2% | — |
| DTBench | — | 45.7% |
| LiveBench Data Analysis | 36.4% | — |
| Epoch Capabilities Index | 119.83 | — |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math Ministral 8B leads
Gemma 2 9B: 9.9 (#318), Ministral 8B: 25.7 (#267)
| Benchmark | Gemma 2 9B | Ministral 8B |
|---|---|---|
| LMArena Math | 1183 | 1188 |
| MATH Level 5 | 21% | 14.9% |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| LiveBench Math | 19.8% | — |
| GSM8K | 84.9% | — |
Knowledge Ministral 8B leads
Gemma 2 9B: 9.7 (#305), Ministral 8B: 12.6 (#297)
| Benchmark | Gemma 2 9B | Ministral 8B |
|---|---|---|
| GPQA Diamond | 27.5% | 27.1% |
| LMArena Expert | 1147 | 1170 |
| Vectara Hallucination Rate | — | 7.4% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multilingual Gemma 2 9B leads
Gemma 2 9B: 36.6 (#238), Ministral 8B: 35.1 (#247)
| Benchmark | Gemma 2 9B | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1188 | 1165 |
| LMArena Chinese | 1185 | 1193 |
| LMArena Russian | 1200 | 1195 |
| LMArena French | 1190 | — |
| LMArena German | 1186 | — |
| LMArena Japanese | 1144 | — |
| LMArena Korean | 1137 | — |
| LMArena Spanish | 1200 | — |
Instruction Following Ministral 8B leads
Gemma 2 9B: 57.6 (#269), Ministral 8B: 60.5 (#250)
| Benchmark | Gemma 2 9B | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1178 | 1161 |
| LiveBench Instruction Following | 52.6% | — |
Long Context Too close to call
Gemma 2 9B: 36.3 (#233), Ministral 8B: 36.7 (#227)
| Benchmark | Gemma 2 9B | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1197 | 1212 |
Writing & Preference Ministral 8B leads
Gemma 2 9B: 32.1 (#281), Ministral 8B: 39.6 (#246)
| Benchmark | Gemma 2 9B | Ministral 8B |
|---|---|---|
| LMArena Text | 1207 | 1191 |
| LMArena Creative Writing | 1206 | 1175 |
| LMArena Multi-Turn | 1193 | 1166 |
| EQ-Bench Creative Writing | 841 | — |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Ministral 8B?
Ministral 8B is the stronger model overall, scoring 28.2 to 25.9 on the Noometry Index.
Is Gemma 2 9B or Ministral 8B better for coding?
Ministral 8B scores higher on coding benchmarks: 35.0 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and Ministral 8B share?
14 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Ministral 8B has 17.