Model comparison
Devstral Small 2505 vs Gemma 2 9B
Devstral Small 2505 is the stronger model overall, scoring 34.3 to 25.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
GoogleSummary
- The widest gap is in coding, where Devstral Small 2505 leads 38.9 to 29.4.
Side by side
| Devstral Small 2505 | Gemma 2 9B | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 34.3 | 25.9 |
| Released | 2025-05-07 | 2024-06-24 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 4 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Devstral Small 2505 leads
Devstral Small 2505: 38.9 (#166), Gemma 2 9B: 29.4 (#304)
| Benchmark | Devstral Small 2505 | Gemma 2 9B |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| BigCodeBench Instruct | — | 34.7% |
| LiveBench Coding | — | 22.5% |
| LMArena Coding | — | 1173 |
| BigCodeBench Complete | — | 40.6% |
Reasoning Devstral Small 2505 leads
Devstral Small 2505: 19.7 (#252), Gemma 2 9B: 15.9 (#309)
| Benchmark | Devstral Small 2505 | Gemma 2 9B |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | — | 15.2% |
| LMArena Hard Prompts | — | 1171 |
| LiveBench Data Analysis | — | 36.4% |
| Epoch Capabilities Index | — | 119.83 |
| LiveBench | — | 28.7% |
| PIQA | — | 83.7% |
Math Not comparable
Devstral Small 2505: —, Gemma 2 9B: 9.9 (#318)
| Benchmark | Devstral Small 2505 | Gemma 2 9B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 0.6% |
| LiveBench Math | — | 19.8% |
| LMArena Math | — | 1183 |
| MATH Level 5 | — | 21% |
| GSM8K | — | 84.9% |
Knowledge Not comparable
Devstral Small 2505: —, Gemma 2 9B: 9.7 (#305)
| Benchmark | Devstral Small 2505 | Gemma 2 9B |
|---|---|---|
| GPQA Diamond | — | 27.5% |
| LMArena Expert | — | 1147 |
| BoolQ | — | 85.7% |
| MMLU | — | 72.1% |
Multilingual Not comparable
Devstral Small 2505: —, Gemma 2 9B: 36.6 (#238)
| Benchmark | Devstral Small 2505 | Gemma 2 9B |
|---|---|---|
| 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
Devstral Small 2505: —, Gemma 2 9B: 57.6 (#269)
| Benchmark | Devstral Small 2505 | Gemma 2 9B |
|---|---|---|
| LiveBench Instruction Following | — | 52.6% |
| LMArena Instruction Following | — | 1178 |
Long Context Not comparable
Devstral Small 2505: —, Gemma 2 9B: 36.3 (#233)
| Benchmark | Devstral Small 2505 | Gemma 2 9B |
|---|---|---|
| LMArena Longer Query | — | 1197 |
Writing & Preference Not comparable
Devstral Small 2505: —, Gemma 2 9B: 32.1 (#281)
| Benchmark | Devstral Small 2505 | Gemma 2 9B |
|---|---|---|
| LMArena Text | — | 1207 |
| LMArena Creative Writing | — | 1206 |
| EQ-Bench Creative Writing | — | 841 |
| LMArena Multi-Turn | — | 1193 |
| LiveBench Language | — | 25.5% |
Frequently asked questions
Is Devstral Small 2505 better than Gemma 2 9B?
Devstral Small 2505 is the stronger model overall, scoring 34.3 to 25.9 on the Noometry Index.
Is Devstral Small 2505 or Gemma 2 9B better for coding?
Devstral Small 2505 scores higher on coding benchmarks: 38.9 versus 29.4 in the Noometry coding category.
How many benchmarks do Devstral Small 2505 and Gemma 2 9B share?
0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Gemma 2 9B has 35.