Model comparison
Gemini 2.5 Flash vs Mistral Large 3
Gemini 2.5 Flash and Mistral Large 3 score almost the same on the Noometry Index (39.3 vs 39.1), so choose on price, context window or the category you care about most.
Last verified . 21 shared benchmarks.
Google
Mistral AISummary
- They share 21 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 7 categories and Mistral Large 3 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Large 3 leads 60.0 to 53.8.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 7.8% for Gemini 2.5 Flash and 14.5% for Mistral Large 3.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.30 / $2.50 for Gemini 2.5 Flash.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 262K.
- Mistral Large 3 has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash | Mistral Large 3 | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 39.3 | 39.1 |
| Released | 2025-04-17 | 2025-12-02 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 8K |
| Input $ / M tokens | $0.30 | $0.25 |
| Output $ / M tokens | $2.50 | $0.75 |
| Results tracked | 54 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Flash leads
Gemini 2.5 Flash: 35.8 (#220), Mistral Large 3: 34.4 (#237)
| Benchmark | Gemini 2.5 Flash | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1424 | 1448 |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1230 |
| WeirdML | 41.9% | — |
| ALE-Bench | 661.88 | — |
Agentic & Tool Use Not comparable
Gemini 2.5 Flash: 30.8 (#74), Mistral Large 3: —
| Benchmark | Gemini 2.5 Flash | Mistral Large 3 |
|---|---|---|
| Terminal-Bench | 17.1% | — |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |
Reasoning Gemini 2.5 Flash leads
Gemini 2.5 Flash: 18.1 (#286), Mistral Large 3: 15.2 (#319)
| Benchmark | Gemini 2.5 Flash | Mistral Large 3 |
|---|---|---|
| Kagi LLM Benchmark | 56.8% | 50.9% |
| LMArena Hard Prompts | 1422 | 1429 |
| ARC-AGI-2 | 2.5% | — |
| SimpleBench | 41.2% | — |
| NYT Connections (extended) | — | 7.5% |
| ARC-AGI-1 | 33.3% | — |
| CritPt | 1.1% | — |
| EnigmaEval | 2.7% | — |
| Thematic Generalization | — | 23% |
| DTBench | 76.5% | — |
| LMCA | 27.5% | — |
| Epoch Capabilities Index | 143.03 | — |
| ForecastBench | 60.6 | — |
Math Gemini 2.5 Flash leads
Gemini 2.5 Flash: 39.9 (#98), Mistral Large 3: 38.7 (#129)
| Benchmark | Gemini 2.5 Flash | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1415 | 1414 |
| OTIS Mock AIME 2024-2025 | 73.1% | — |
| Omni-MATH | 38.5% | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Too close to call
Gemini 2.5 Flash: 36.4 (#168), Mistral Large 3: 36.0 (#177)
| Benchmark | Gemini 2.5 Flash | Mistral Large 3 |
|---|---|---|
| Vectara Hallucination Rate | 7.8% | 14.5% |
| LMArena Expert | 1426 | 1421 |
| Humanity's Last Exam | 12.1% | — |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| GPQA (HELM) | 39% | — |
Multimodal Gemini 2.5 Flash leads
Gemini 2.5 Flash: 41.8 (#32), Mistral Large 3: 38.2 (#66)
| Benchmark | Gemini 2.5 Flash | Mistral Large 3 |
|---|---|---|
| LMArena Vision | 1253 | 1221 |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Too close to call
Gemini 2.5 Flash: 52.3 (#88), Mistral Large 3: 52.5 (#84)
| Benchmark | Gemini 2.5 Flash | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1409 | 1413 |
| LMArena Chinese | 1450 | 1447 |
| LMArena French | 1433 | 1455 |
| LMArena German | 1418 | 1437 |
| LMArena Japanese | 1405 | 1394 |
| LMArena Korean | 1385 | 1384 |
| LMArena Russian | 1415 | 1411 |
| LMArena Spanish | 1421 | 1440 |
Instruction Following Gemini 2.5 Flash leads
Gemini 2.5 Flash: 75.7 (#54), Mistral Large 3: 74.0 (#108)
| Benchmark | Gemini 2.5 Flash | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1405 | 1403 |
| IFEval | 89.8% | — |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#17), Mistral Large 3: 43.1 (#105)
| Benchmark | Gemini 2.5 Flash | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1419 | 1413 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference Mistral Large 3 leads
Gemini 2.5 Flash: 53.8 (#157), Mistral Large 3: 60.0 (#101)
| Benchmark | Gemini 2.5 Flash | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1417 | 1428 |
| LMArena Creative Writing | 1400 | 1386 |
| EQ-Bench Creative Writing | 1137 | 1412 |
| LMArena Multi-Turn | 1408 | 1429 |
| Short-Story Creative Writing | 76.5% | — |
| WildBench | 81.7% | — |
Frequently asked questions
Is Gemini 2.5 Flash better than Mistral Large 3?
Gemini 2.5 Flash and Mistral Large 3 score almost the same on the Noometry Index (39.3 vs 39.1), so choose on price, context window or the category you care about most.
Which is cheaper, Gemini 2.5 Flash or Mistral Large 3?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Gemini 2.5 Flash lists at $0.30 and $2.50.
Is Gemini 2.5 Flash or Mistral Large 3 better for coding?
Gemini 2.5 Flash scores higher on coding benchmarks: 35.8 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 2.5 Flash and Mistral Large 3 share?
21 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Mistral Large 3 has 24.