Model comparison
Devstral Small 2505 vs Gemini 2.0 Flash-Lite
Gemini 2.0 Flash-Lite is the stronger model overall, scoring 37.8 to 34.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
GoogleSummary
- Devstral Small 2505 has downloadable open weights; the other is API-only.
Side by side
| Devstral Small 2505 | Gemini 2.0 Flash-Lite | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 34.3 | 37.8 |
| Released | 2025-05-07 | 2025-02-05 |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 4 | 32 |
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), Gemini 2.0 Flash-Lite: 37.9 (#185)
| Benchmark | Devstral Small 2505 | Gemini 2.0 Flash-Lite |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| LiveBench Coding | — | 47.1% |
| LMArena Coding | — | 1322 |
Reasoning Gemini 2.0 Flash-Lite leads
Devstral Small 2505: 19.7 (#252), Gemini 2.0 Flash-Lite: 22.0 (#210)
| Benchmark | Devstral Small 2505 | Gemini 2.0 Flash-Lite |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | — | 50.1% |
| LMArena Hard Prompts | — | 1324 |
| DTBench | — | 52.5% |
| LiveBench Data Analysis | — | 65.5% |
| ForecastBench | — | 57.1 |
| LiveBench | — | 54.3% |
Math Not comparable
Devstral Small 2505: —, Gemini 2.0 Flash-Lite: 34.1 (#196)
| Benchmark | Devstral Small 2505 | Gemini 2.0 Flash-Lite |
|---|---|---|
| Omni-MATH | — | 37.4% |
| LiveBench Math | — | 58.1% |
| LMArena Math | — | 1309 |
Knowledge Not comparable
Devstral Small 2505: —, Gemini 2.0 Flash-Lite: 35.0 (#189)
| Benchmark | Devstral Small 2505 | Gemini 2.0 Flash-Lite |
|---|---|---|
| MMLU-Pro | — | 72% |
| GPQA (HELM) | — | 50% |
| LMArena Expert | — | 1305 |
Multimodal Not comparable
Devstral Small 2505: —, Gemini 2.0 Flash-Lite: 31.2 (#109)
| Benchmark | Devstral Small 2505 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Vision | — | 1100 |
Multilingual Not comparable
Devstral Small 2505: —, Gemini 2.0 Flash-Lite: 46.0 (#161)
| Benchmark | Devstral Small 2505 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Non-English | — | 1323 |
| LMArena Chinese | — | 1339 |
| LMArena French | — | 1347 |
| LMArena German | — | 1306 |
| LMArena Japanese | — | 1301 |
| LMArena Korean | — | 1325 |
| LMArena Russian | — | 1328 |
| LMArena Spanish | — | 1313 |
Instruction Following Not comparable
Devstral Small 2505: —, Gemini 2.0 Flash-Lite: 70.4 (#163)
| Benchmark | Devstral Small 2505 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LiveBench Instruction Following | — | 78.3% |
| IFEval | — | 82.4% |
| LMArena Instruction Following | — | 1305 |
Long Context Not comparable
Devstral Small 2505: —, Gemini 2.0 Flash-Lite: 40.1 (#160)
| Benchmark | Devstral Small 2505 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Longer Query | — | 1320 |
Writing & Preference Not comparable
Devstral Small 2505: —, Gemini 2.0 Flash-Lite: 51.7 (#177)
| Benchmark | Devstral Small 2505 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Text | — | 1330 |
| LMArena Creative Writing | — | 1319 |
| WildBench | — | 79% |
| LMArena Multi-Turn | — | 1307 |
| LiveBench Language | — | 34.3% |
Frequently asked questions
Is Devstral Small 2505 better than Gemini 2.0 Flash-Lite?
Gemini 2.0 Flash-Lite is the stronger model overall, scoring 37.8 to 34.3 on the Noometry Index.
Is Devstral Small 2505 or Gemini 2.0 Flash-Lite better for coding?
Devstral Small 2505 scores higher on coding benchmarks: 38.9 versus 37.9 in the Noometry coding category.
How many benchmarks do Devstral Small 2505 and Gemini 2.0 Flash-Lite share?
0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Gemini 2.0 Flash-Lite has 32.