Model comparison
Devstral Small 2505 vs Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 34.3 on the Noometry Index. Devstral Small 2505 costs 30× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Mistral AI
GoogleSummary
- They share 2 benchmarks with published results for both. Devstral Small 2505 scores higher in 0 categories and Gemini 3.1 Pro Preview in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 19.7.
- The biggest single-benchmark swing is SciCode: 28.8% for Devstral Small 2505 and 58.9% for Gemini 3.1 Pro Preview.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
- Gemini 3.1 Pro Preview 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 Pro Preview | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 34.3 | 56.7 |
| Released | 2025-05-07 | 2026-02-19 |
| Weights | Open | Proprietary |
| Context window | 128K | 1.05M |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.10 | $2 |
| Output $ / M tokens | $0.30 | $12 |
| Results tracked | 4 | 71 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.1 Pro Preview leads
Devstral Small 2505: 38.9 (#166), Gemini 3.1 Pro Preview: 42.5 (#99)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Pro Preview |
|---|---|---|
| SciCode | 28.8% | 58.9% |
| SWE-bench Verified | — | 75.6% |
| DeepSWE | — | 11.7% |
| SWE-bench Verified (bash only) | 56.4% | — |
| LMArena WebDev | — | 1447 |
| GSO | — | 22.6% |
| WeirdML | — | 72.1% |
| LMArena Coding | — | 1484 |
| MirrorCode | — | 8.9% |
| ALE-Bench | — | 1,161 |
| AlgoTune | — | 2.02 |
Agentic & Tool Use Not comparable
Devstral Small 2505: —, Gemini 3.1 Pro Preview: 37.7 (#34)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Pro Preview |
|---|---|---|
| Terminal-Bench | — | 80.2% |
| APEX-Agents | — | 35.3% |
| τ²-bench Banking | — | 26% |
| DeepResearch Bench | — | 47.8% |
| PostTrainBench | — | 22% |
| BALROG | — | 57% |
| ExploitBench | — | 26.1% |
| GBAEval | — | 0.8% |
| GDP.pdf | — | 17% |
| LMArena Search | — | 1211 |
| METR Time Horizons | — | 77% |
| Vending-Bench 2 | — | 3,774 |
Reasoning Gemini 3.1 Pro Preview leads
Devstral Small 2505: 19.7 (#252), Gemini 3.1 Pro Preview: 71.7 (#12)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Pro Preview |
|---|---|---|
| CritPt | 0% | 17.7% |
| ARC-AGI-2 | — | 77.1% |
| SimpleBench | — | 79.6% |
| Kagi LLM Benchmark | 37.7% | — |
| NYT Connections (extended) | — | 97.4% |
| ARC-AGI-1 | — | 98% |
| Chess Puzzles | — | 55% |
| EnigmaEval | — | 36.8% |
| Thematic Generalization | — | 79.4% |
| EBR-Bench | — | 14.3% |
| LMArena Hard Prompts | — | 1485 |
| Mystery Game Puzzles | — | 34% |
| DTBench | — | 97.1% |
| LMCA | — | 53.8% |
| Epoch Capabilities Index | — | 154.77 |
| ForecastBench | — | 59 |
Math Not comparable
Devstral Small 2505: —, Gemini 3.1 Pro Preview: 62.1 (#34)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Pro Preview |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 59.6% |
| FrontierMath Tier 4 | — | 26.8% |
| MathArena Final-Answer Competitions | — | 86.5% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 26% |
| LMArena Math | — | 1485 |
| FrontierMath (Feb 2025 set) | — | 36.9% |
| FrontierMath Tier 4 (v1) | — | 16.7% |
Knowledge Not comparable
Devstral Small 2505: —, Gemini 3.1 Pro Preview: 71.8 (#3)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Pro Preview |
|---|---|---|
| GPQA Diamond | — | 94.4% |
| Humanity's Last Exam | — | 46.4% |
| SimpleQA Verified | — | 73.5% |
| Vectara Hallucination Rate | — | 10.4% |
| LMArena Expert | — | 1485 |
Multimodal Not comparable
Devstral Small 2505: —, Gemini 3.1 Pro Preview: 37.9 (#69)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Vision | — | 1296 |
| Blueprint-Bench 2 | — | 26.5% |
| Furniture Assembly | — | 26.7% |
| LMArena Document | — | 1444 |
Multilingual Not comparable
Devstral Small 2505: —, Gemini 3.1 Pro Preview: 57.0 (#12)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Non-English | — | 1477 |
| LMArena Chinese | — | 1529 |
| LMArena French | — | 1487 |
| LMArena German | — | 1491 |
| LMArena Japanese | — | 1493 |
| LMArena Korean | — | 1455 |
| LMArena Russian | — | 1498 |
| LMArena Spanish | — | 1479 |
Instruction Following Not comparable
Devstral Small 2505: —, Gemini 3.1 Pro Preview: 77.0 (#32)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Instruction Following | — | 1466 |
Long Context Not comparable
Devstral Small 2505: —, Gemini 3.1 Pro Preview: 47.4 (#18)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Pro Preview |
|---|---|---|
| CL-bench | — | 20.8% |
| CL-bench Life | — | 16.9% |
| LMArena Longer Query | — | 1483 |
Writing & Preference Not comparable
Devstral Small 2505: —, Gemini 3.1 Pro Preview: 66.1 (#37)
| Benchmark | Devstral Small 2505 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Text | — | 1481 |
| LMArena Creative Writing | — | 1482 |
| EQ-Bench Creative Writing | — | 1491 |
| EQ-Bench 4 | — | 1142 |
| LMArena Multi-Turn | — | 1488 |
Frequently asked questions
Is Devstral Small 2505 better than Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 34.3 on the Noometry Index. Devstral Small 2505 costs 30× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.
Which is cheaper, Devstral Small 2505 or Gemini 3.1 Pro Preview?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.
Is Devstral Small 2505 or Gemini 3.1 Pro Preview better for coding?
Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 38.9 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.1 Pro Preview does, with 1.05M tokens against 128K.
How many benchmarks do Devstral Small 2505 and Gemini 3.1 Pro Preview share?
2 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Gemini 3.1 Pro Preview has 71.