Model comparison
Gemini 3.1 Flash Lite vs Mistral Medium
Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 36.3 on the Noometry Index.
Last verified . 29 shared benchmarks.
Google
Mistral AISummary
- They share 29 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 7 categories and Mistral Medium in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3.1 Flash Lite leads 41.9 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 80% for Gemini 3.1 Flash Lite and 32.2% for Mistral Medium.
- Gemini 3.1 Flash Lite is cheaper at $0.25 / $1.50 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 262K.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.1 Flash Lite | Mistral Medium | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 40.8 | 36.3 |
| Released | 2026-03-03 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 262K |
| Input $ / M tokens | $0.25 | $1.50 |
| Output $ / M tokens | $1.50 | $7.50 |
| Results tracked | 38 | 36 |
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 Medium: 34.2 (#243)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Medium |
|---|---|---|
| SciCode | 41.9% | 40.2% |
| WeirdML | 52.2% | 43.7% |
| LMArena Coding | 1400 | 1434 |
| ALE-Bench | 797.73 | 763.98 |
| FrontierCode | — | 8% |
| LMArena WebDev | 1256 | — |
Agentic & Tool Use Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 30.2 (#79), Mistral Medium: 28.3 (#90)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
| DeepResearch Bench | 37.3% | — |
Reasoning Mistral Medium leads
Gemini 3.1 Flash Lite: 22.9 (#186), Mistral Medium: 24.0 (#167)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 67.2% | 50% |
| CritPt | 1.1% | 0% |
| LMArena Hard Prompts | 1407 | 1426 |
| DTBench | 76.8% | 75.5% |
| LMCA | 35% | 26.1% |
| NYT Connections (extended) | 8.2% | — |
| Chess Puzzles | 25% | — |
| EnigmaEval | 3% | — |
| Thematic Generalization | 63.3% | — |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 144.47 | — |
| ForecastBench | 54.4 | — |
Math Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 40.7 (#90), Mistral Medium: 28.1 (#245)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 32.2% |
| LMArena Math | 1428 | 1408 |
| FrontierMath (Tiers 1-3) | 27.7% | — |
| ProofBench | — | 9% |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 41.9 (#104), Mistral Medium: 25.0 (#265)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Medium |
|---|---|---|
| GPQA Diamond | 81.8% | 59.5% |
| Humanity's Last Exam | 8.6% | 4.5% |
| Vectara Hallucination Rate | 8.2% | 22.7% |
| LMArena Expert | 1398 | 1408 |
Multimodal Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 39.4 (#60), Mistral Medium: 35.3 (#88)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Medium |
|---|---|---|
| LMArena Vision | 1240 | 1172 |
Multilingual Too close to call
Gemini 3.1 Flash Lite: 52.3 (#86), Mistral Medium: 52.1 (#91)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1411 | 1408 |
| LMArena Chinese | 1461 | 1447 |
| LMArena French | 1424 | 1459 |
| LMArena German | 1429 | 1432 |
| LMArena Japanese | 1413 | 1378 |
| LMArena Korean | 1392 | 1380 |
| LMArena Russian | 1420 | 1411 |
| LMArena Spanish | 1421 | 1433 |
Instruction Following Mistral Medium leads
Gemini 3.1 Flash Lite: 72.7 (#131), Mistral Medium: 73.7 (#116)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1377 | 1398 |
Long Context Too close to call
Gemini 3.1 Flash Lite: 42.5 (#122), Mistral Medium: 42.9 (#114)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1394 | 1406 |
Writing & Preference Too close to call
Gemini 3.1 Flash Lite: 60.9 (#94), Mistral Medium: 60.0 (#103)
| Benchmark | Gemini 3.1 Flash Lite | Mistral Medium |
|---|---|---|
| LMArena Text | 1416 | 1424 |
| LMArena Creative Writing | 1401 | 1391 |
| LMArena Multi-Turn | 1417 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than Mistral Medium?
Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 36.3 on the Noometry Index.
Which is cheaper, Gemini 3.1 Flash Lite or Mistral Medium?
Gemini 3.1 Flash Lite is cheaper. It lists at $0.25 per million input tokens and $1.50 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Gemini 3.1 Flash Lite or Mistral Medium better for coding?
Gemini 3.1 Flash Lite scores higher on coding benchmarks: 37.8 versus 34.2 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 Medium share?
29 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Mistral Medium has 36.