Model comparison
Gemma 2 9B vs Mistral Medium
Mistral Medium is the stronger model overall, scoring 36.3 to 25.9 on the Noometry Index.
Last verified . 20 shared benchmarks.
Google
Mistral AISummary
- They share 20 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Mistral Medium in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.0 to 32.1.
- The biggest single-benchmark swing is MATH Level 5: 21% for Gemma 2 9B and 81.6% for Mistral Medium.
Side by side
| Gemma 2 9B | Mistral Medium | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 25.9 | 36.3 |
| Released | 2024-06-24 | 2023-12-11 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $1.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 35 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium leads
Gemma 2 9B: 29.4 (#304), Mistral Medium: 34.2 (#243)
| Benchmark | Gemma 2 9B | Mistral Medium |
|---|---|---|
| LMArena Coding | 1173 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Not comparable
Gemma 2 9B: —, Mistral Medium: 28.3 (#90)
| Benchmark | Gemma 2 9B | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning Mistral Medium leads
Gemma 2 9B: 15.9 (#309), Mistral Medium: 24.0 (#167)
| Benchmark | Gemma 2 9B | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1426 |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| LiveBench Reasoning | 15.2% | — |
| DTBench | — | 75.5% |
| LiveBench Data Analysis | 36.4% | — |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 119.83 | — |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math Mistral Medium leads
Gemma 2 9B: 9.9 (#318), Mistral Medium: 28.1 (#245)
| Benchmark | Gemma 2 9B | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 32.2% |
| LMArena Math | 1183 | 1408 |
| MATH Level 5 | 21% | 81.6% |
| ProofBench | — | 9% |
| LiveBench Math | 19.8% | — |
| FrontierMath (Feb 2025 set) | — | 0.3% |
| GSM8K | 84.9% | — |
Knowledge Mistral Medium leads
Gemma 2 9B: 9.7 (#305), Mistral Medium: 25.0 (#265)
| Benchmark | Gemma 2 9B | Mistral Medium |
|---|---|---|
| GPQA Diamond | 27.5% | 59.5% |
| LMArena Expert | 1147 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multimodal Not comparable
Gemma 2 9B: —, Mistral Medium: 35.3 (#88)
| Benchmark | Gemma 2 9B | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Mistral Medium leads
Gemma 2 9B: 36.6 (#238), Mistral Medium: 52.1 (#91)
| Benchmark | Gemma 2 9B | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1188 | 1408 |
| LMArena Chinese | 1185 | 1447 |
| LMArena French | 1190 | 1459 |
| LMArena German | 1186 | 1432 |
| LMArena Japanese | 1144 | 1378 |
| LMArena Korean | 1137 | 1380 |
| LMArena Russian | 1200 | 1411 |
| LMArena Spanish | 1200 | 1433 |
Instruction Following Mistral Medium leads
Gemma 2 9B: 57.6 (#269), Mistral Medium: 73.7 (#116)
| Benchmark | Gemma 2 9B | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1178 | 1398 |
| LiveBench Instruction Following | 52.6% | — |
Long Context Mistral Medium leads
Gemma 2 9B: 36.3 (#233), Mistral Medium: 42.9 (#114)
| Benchmark | Gemma 2 9B | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1197 | 1406 |
Writing & Preference Mistral Medium leads
Gemma 2 9B: 32.1 (#281), Mistral Medium: 60.0 (#103)
| Benchmark | Gemma 2 9B | Mistral Medium |
|---|---|---|
| LMArena Text | 1207 | 1424 |
| LMArena Creative Writing | 1206 | 1391 |
| LMArena Multi-Turn | 1193 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| EQ-Bench Creative Writing | 841 | — |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Mistral Medium?
Mistral Medium is the stronger model overall, scoring 36.3 to 25.9 on the Noometry Index.
Is Gemma 2 9B or Mistral Medium better for coding?
Mistral Medium scores higher on coding benchmarks: 34.2 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and Mistral Medium share?
20 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Mistral Medium has 36.