Model comparison
Gemma 2 9B vs Mistral Small
Mistral Small is the stronger model overall, scoring 33.1 to 25.7 on the Noometry Index.
Last verified . 30 shared benchmarks.
Google
Mistral AISummary
- They share 30 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Mistral Small in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small leads 30.9 to 9.7.
- The biggest single-benchmark swing is LiveBench Reasoning: 15.2% for Gemma 2 9B and 44.8% for Mistral Small.
Side by side
| Gemma 2 9B | Mistral Small | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 25.7 | 33.1 |
| Released | 2024-06-24 | 2024-02-26 |
| Weights | Open | Open |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 35 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small leads
Gemma 2 9B: 29.0 (#299), Mistral Small: 33.5 (#242)
| Benchmark | Gemma 2 9B | Mistral Small |
|---|---|---|
| BigCodeBench Instruct | 34.7% | 36.1% |
| LiveBench Coding | 22.5% | 36.2% |
| LMArena Coding | 1174 | 1363 |
| BigCodeBench Complete | 40.6% | 46.6% |
| SciCode | — | 26.5% |
| ALE-Bench | — | 497.62 |
Agentic & Tool Use Not comparable
Gemma 2 9B: —, Mistral Small: 27.9 (#87)
| Benchmark | Gemma 2 9B | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
Reasoning Mistral Small leads
Gemma 2 9B: 15.3 (#306), Mistral Small: 19.3 (#238)
| Benchmark | Gemma 2 9B | Mistral Small |
|---|---|---|
| LiveBench Reasoning | 15.2% | 44.8% |
| LMArena Hard Prompts | 1172 | 1336 |
| LiveBench Data Analysis | 36.4% | 53.7% |
| LiveBench | 28.7% | 44% |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| DTBench | — | 70.9% |
| LMCA | — | 20.6% |
| Epoch Capabilities Index | 119.78 | — |
| PIQA | 83.7% | — |
Math Mistral Small leads
Gemma 2 9B: 9.3 (#312), Mistral Small: 15.4 (#287)
| Benchmark | Gemma 2 9B | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 5.8% |
| LiveBench Math | 19.8% | 39.9% |
| LMArena Math | 1183 | 1341 |
| MATH Level 5 | 21% | 46.8% |
| GSM8K | 84.9% | — |
Knowledge Mistral Small leads
Gemma 2 9B: 9.7 (#300), Mistral Small: 30.9 (#214)
| Benchmark | Gemma 2 9B | Mistral Small |
|---|---|---|
| GPQA Diamond | 27.5% | 47.5% |
| LMArena Expert | 1147 | 1293 |
| MMLU | 72.1% | 68.7% |
| Vectara Hallucination Rate | — | 5.1% |
| BoolQ | 85.7% | — |
Multimodal Not comparable
Gemma 2 9B: —, Mistral Small: 32.9 (#91)
| Benchmark | Gemma 2 9B | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual Mistral Small leads
Gemma 2 9B: 36.8 (#233), Mistral Small: 45.7 (#164)
| Benchmark | Gemma 2 9B | Mistral Small |
|---|---|---|
| LMArena Non-English | 1188 | 1315 |
| LMArena Chinese | 1185 | 1342 |
| LMArena French | 1189 | 1337 |
| LMArena German | 1186 | 1341 |
| LMArena Japanese | 1144 | 1275 |
| LMArena Korean | 1137 | 1260 |
| LMArena Russian | 1200 | 1324 |
| LMArena Spanish | 1200 | 1346 |
Instruction Following Mistral Small leads
Gemma 2 9B: 57.8 (#264), Mistral Small: 66.6 (#204)
| Benchmark | Gemma 2 9B | Mistral Small |
|---|---|---|
| LiveBench Instruction Following | 52.6% | 63.7% |
| LMArena Instruction Following | 1178 | 1310 |
Long Context Mistral Small leads
Gemma 2 9B: 36.3 (#228), Mistral Small: 40.4 (#151)
| Benchmark | Gemma 2 9B | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1197 | 1327 |
Writing & Preference Mistral Small leads
Gemma 2 9B: 32.3 (#276), Mistral Small: 52.6 (#165)
| Benchmark | Gemma 2 9B | Mistral Small |
|---|---|---|
| LMArena Text | 1207 | 1338 |
| LMArena Creative Writing | 1206 | 1304 |
| LMArena Multi-Turn | 1193 | 1344 |
| LiveBench Language | 25.5% | 30.5% |
| EQ-Bench Creative Writing | 841 | — |
Frequently asked questions
Is Gemma 2 9B better than Mistral Small?
Mistral Small is the stronger model overall, scoring 33.1 to 25.7 on the Noometry Index.
Is Gemma 2 9B or Mistral Small better for coding?
Mistral Small scores higher on coding benchmarks: 33.5 versus 29.0 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and Mistral Small share?
30 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Mistral Small has 39.