Model comparison
Gemini 3.1 Flash Lite vs Mistral Small
Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 33.4 on the Noometry Index. Mistral Small costs 2.1× 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 . 27 shared benchmarks.
Google
Mistral AISummary
- They share 27 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 10 categories and Mistral Small in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 3.1 Flash Lite leads 40.7 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 80% for Gemini 3.1 Flash Lite and 5.8% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 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 262K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.1 Flash Lite | Mistral Small | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 40.8 | 33.4 |
| Released | 2026-03-03 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 256K |
| Input $ / M tokens | $0.25 | $0.15 |
| Output $ / M tokens | $1.50 | $0.60 |
| Results tracked | 38 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 37.8 (#188), Mistral Small: 34.0 (#247)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Small |
|---|---|---|
| SciCode | 41.9% | 26.5% |
| LMArena Coding | 1400 | 1362 |
| ALE-Bench | 797.73 | 497.62 |
| LMArena WebDev | 1256 | — |
| WeirdML | 52.2% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
Agentic & Tool Use Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 30.2 (#79), Mistral Small: 28.1 (#93)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
| DeepResearch Bench | 37.3% | — |
Reasoning Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 22.9 (#186), Mistral Small: 19.8 (#250)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 67.2% | 37.8% |
| CritPt | 1.1% | 0% |
| LMArena Hard Prompts | 1407 | 1335 |
| DTBench | 76.8% | 70.9% |
| LMCA | 35% | 20.6% |
| NYT Connections (extended) | 8.2% | — |
| Chess Puzzles | 25% | — |
| EnigmaEval | 3% | — |
| Thematic Generalization | 63.3% | — |
| LiveBench Reasoning | — | 44.8% |
| LiveBench Data Analysis | — | 53.7% |
| Epoch Capabilities Index | 144.47 | — |
| ForecastBench | 54.4 | — |
| LiveBench | — | 44% |
Math Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 40.7 (#90), Mistral Small: 16.4 (#293)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 5.8% |
| LMArena Math | 1428 | 1341 |
| FrontierMath (Tiers 1-3) | 27.7% | — |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |
Knowledge Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 41.9 (#104), Mistral Small: 31.0 (#222)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Small |
|---|---|---|
| GPQA Diamond | 81.8% | 47.5% |
| Vectara Hallucination Rate | 8.2% | 5.1% |
| LMArena Expert | 1398 | 1291 |
| Humanity's Last Exam | 8.6% | — |
| MMLU | — | 68.7% |
Multimodal Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 39.4 (#60), Mistral Small: 33.5 (#96)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Small |
|---|---|---|
| LMArena Vision | 1240 | 1142 |
Multilingual Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 52.3 (#86), Mistral Small: 45.5 (#169)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Small |
|---|---|---|
| LMArena Non-English | 1411 | 1315 |
| LMArena Chinese | 1461 | 1340 |
| LMArena French | 1424 | 1337 |
| LMArena German | 1429 | 1340 |
| LMArena Japanese | 1413 | 1275 |
| LMArena Korean | 1392 | 1259 |
| LMArena Russian | 1420 | 1324 |
| LMArena Spanish | 1421 | 1346 |
Instruction Following Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 72.7 (#131), Mistral Small: 66.4 (#209)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1377 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 42.5 (#122), Mistral Small: 40.4 (#156)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1394 | 1327 |
Writing & Preference Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 60.9 (#94), Mistral Small: 52.5 (#171)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Small |
|---|---|---|
| LMArena Text | 1416 | 1338 |
| LMArena Creative Writing | 1401 | 1305 |
| LMArena Multi-Turn | 1417 | 1344 |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than Mistral Small?
Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 33.4 on the Noometry Index. Mistral Small costs 2.1× 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, Gemini 3.1 Flash Lite or Mistral Small?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Gemini 3.1 Flash Lite lists at $0.25 and $1.50.
Is Gemini 3.1 Flash Lite or Mistral Small better for coding?
Gemini 3.1 Flash Lite scores higher on coding benchmarks: 37.8 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.1 Flash Lite does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 3.1 Flash Lite and Mistral Small share?
27 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Mistral Small has 39.