Model comparison
Devstral Small 2505 vs Gemini 3.1 Flash Lite
Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 34.3 on the Noometry Index. Devstral Small 2505 costs 3.7× less per token, which makes it the better buy when Gemini 3.1 Flash Lite's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
Mistral AI
GoogleSummary
- They share 3 benchmarks with published results for both. Devstral Small 2505 scores higher in 1 category and Gemini 3.1 Flash Lite in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Flash Lite leads 22.9 to 19.7.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 37.7% for Devstral Small 2505 and 67.2% for Gemini 3.1 Flash Lite.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.25 / $1.50 for Gemini 3.1 Flash Lite.
- Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 128K.
- Devstral Small 2505 has downloadable open weights; the other is API-only.
Side by side
| Devstral Small 2505 | Gemini 3.1 Flash Lite | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 34.3 | 40.8 |
| Released | 2025-05-07 | 2026-03-03 |
| Weights | Open | Proprietary |
| Context window | 128K | 1.05M |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.10 | $0.25 |
| Output $ / M tokens | $0.30 | $1.50 |
| Results tracked | 4 | 38 |
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 3.1 Flash Lite: 37.8 (#188)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Flash Lite |
|---|---|---|
| SciCode | 28.8% | 41.9% |
| SWE-bench Verified (bash only) | 56.4% | — |
| LMArena WebDev | — | 1256 |
| WeirdML | — | 52.2% |
| LMArena Coding | — | 1400 |
| ALE-Bench | — | 797.73 |
Agentic & Tool Use Not comparable
Devstral Small 2505: —, Gemini 3.1 Flash Lite: 30.2 (#79)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Flash Lite |
|---|---|---|
| DeepResearch Bench | — | 37.3% |
Reasoning Gemini 3.1 Flash Lite leads
Devstral Small 2505: 19.7 (#252), Gemini 3.1 Flash Lite: 22.9 (#186)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Flash Lite |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | 67.2% |
| CritPt | 0% | 1.1% |
| NYT Connections (extended) | — | 8.2% |
| Chess Puzzles | — | 25% |
| EnigmaEval | — | 3% |
| Thematic Generalization | — | 63.3% |
| LMArena Hard Prompts | — | 1407 |
| DTBench | — | 76.8% |
| LMCA | — | 35% |
| Epoch Capabilities Index | — | 144.47 |
| ForecastBench | — | 54.4 |
Math Not comparable
Devstral Small 2505: —, Gemini 3.1 Flash Lite: 40.7 (#90)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Flash Lite |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 27.7% |
| OTIS Mock AIME 2024-2025 | — | 80% |
| LMArena Math | — | 1428 |
Knowledge Not comparable
Devstral Small 2505: —, Gemini 3.1 Flash Lite: 41.9 (#104)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Flash Lite |
|---|---|---|
| GPQA Diamond | — | 81.8% |
| Humanity's Last Exam | — | 8.6% |
| Vectara Hallucination Rate | — | 8.2% |
| LMArena Expert | — | 1398 |
Multimodal Not comparable
Devstral Small 2505: —, Gemini 3.1 Flash Lite: 39.4 (#60)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Vision | — | 1240 |
Multilingual Not comparable
Devstral Small 2505: —, Gemini 3.1 Flash Lite: 52.3 (#86)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Non-English | — | 1411 |
| LMArena Chinese | — | 1461 |
| LMArena French | — | 1424 |
| LMArena German | — | 1429 |
| LMArena Japanese | — | 1413 |
| LMArena Korean | — | 1392 |
| LMArena Russian | — | 1420 |
| LMArena Spanish | — | 1421 |
Instruction Following Not comparable
Devstral Small 2505: —, Gemini 3.1 Flash Lite: 72.7 (#131)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Instruction Following | — | 1377 |
Long Context Not comparable
Devstral Small 2505: —, Gemini 3.1 Flash Lite: 42.5 (#122)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Longer Query | — | 1394 |
Writing & Preference Not comparable
Devstral Small 2505: —, Gemini 3.1 Flash Lite: 60.9 (#94)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Text | — | 1416 |
| LMArena Creative Writing | — | 1401 |
| LMArena Multi-Turn | — | 1417 |
Frequently asked questions
Is Devstral Small 2505 better than Gemini 3.1 Flash Lite?
Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 34.3 on the Noometry Index. Devstral Small 2505 costs 3.7× less per token, which makes it the better buy when Gemini 3.1 Flash Lite's lead doesn't matter for your workload.
Which is cheaper, Devstral Small 2505 or Gemini 3.1 Flash Lite?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Gemini 3.1 Flash Lite lists at $0.25 and $1.50.
Is Devstral Small 2505 or Gemini 3.1 Flash Lite better for coding?
Devstral Small 2505 scores higher on coding benchmarks: 38.9 versus 37.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.1 Flash Lite does, with 1.05M tokens against 128K.
How many benchmarks do Devstral Small 2505 and Gemini 3.1 Flash Lite share?
3 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Gemini 3.1 Flash Lite has 38.