Model comparison
Gemini 2.5 Flash vs Ministral 3B
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 26.2 on the Noometry Index. Ministral 3B costs 8.5× less per token, which makes it the better buy when Gemini 2.5 Flash's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
Google
Mistral AISummary
- They share 4 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 2 categories and Ministral 3B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 2.5 Flash leads 36.4 to 10.4.
- The biggest single-benchmark swing is DTBench: 76.5% for Gemini 2.5 Flash and 51.7% for Ministral 3B.
- Ministral 3B is cheaper at $0.10 / $0.10 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 131K.
- Ministral 3B has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash | Ministral 3B | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 39.3 | 26.2 |
| Released | 2025-04-17 | 2024-10-01 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 66K | 262K |
| Input $ / M tokens | $0.30 | $0.10 |
| Output $ / M tokens | $2.50 | $0.10 |
| Results tracked | 54 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemini 2.5 Flash: 35.8 (#220), Ministral 3B: —
| Benchmark | Gemini 2.5 Flash | Ministral 3B |
|---|---|---|
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| WeirdML | 41.9% | — |
| LMArena Coding | 1424 | — |
| ALE-Bench | 661.88 | — |
Agentic & Tool Use Not comparable
Gemini 2.5 Flash: 30.8 (#74), Ministral 3B: —
| Benchmark | Gemini 2.5 Flash | Ministral 3B |
|---|---|---|
| Terminal-Bench | 17.1% | — |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |
Reasoning Too close to call
Gemini 2.5 Flash: 18.1 (#286), Ministral 3B: 18.4 (#282)
| Benchmark | Gemini 2.5 Flash | Ministral 3B |
|---|---|---|
| DTBench | 76.5% | 51.7% |
| LMCA | 27.5% | 5.5% |
| Epoch Capabilities Index | 143.03 | 118.1 |
| ARC-AGI-2 | 2.5% | — |
| SimpleBench | 41.2% | — |
| Kagi LLM Benchmark | 56.8% | — |
| ARC-AGI-1 | 33.3% | — |
| CritPt | 1.1% | — |
| EnigmaEval | 2.7% | — |
| LMArena Hard Prompts | 1422 | — |
| ForecastBench | 60.6 | — |
Math Gemini 2.5 Flash leads
Gemini 2.5 Flash: 39.9 (#98), Ministral 3B: 26.6 (#258)
| Benchmark | Gemini 2.5 Flash | Ministral 3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | — |
| Omni-MATH | 38.5% | — |
| LMArena Math | 1415 | — |
| MATH Level 5 | — | 14.4% |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemini 2.5 Flash leads
Gemini 2.5 Flash: 36.4 (#168), Ministral 3B: 10.4 (#302)
| Benchmark | Gemini 2.5 Flash | Ministral 3B |
|---|---|---|
| Vectara Hallucination Rate | 7.8% | 7.3% |
| GPQA Diamond | — | 25.3% |
| Humanity's Last Exam | 12.1% | — |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| GPQA (HELM) | 39% | — |
| LMArena Expert | 1426 | — |
Multimodal Not comparable
Gemini 2.5 Flash: 41.8 (#32), Ministral 3B: —
| Benchmark | Gemini 2.5 Flash | Ministral 3B |
|---|---|---|
| LMArena Vision | 1253 | — |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Not comparable
Gemini 2.5 Flash: 52.3 (#88), Ministral 3B: —
| Benchmark | Gemini 2.5 Flash | Ministral 3B |
|---|---|---|
| LMArena Non-English | 1409 | — |
| LMArena Chinese | 1450 | — |
| LMArena French | 1433 | — |
| LMArena German | 1418 | — |
| LMArena Japanese | 1405 | — |
| LMArena Korean | 1385 | — |
| LMArena Russian | 1415 | — |
| LMArena Spanish | 1421 | — |
Instruction Following Not comparable
Gemini 2.5 Flash: 75.7 (#54), Ministral 3B: —
| Benchmark | Gemini 2.5 Flash | Ministral 3B |
|---|---|---|
| IFEval | 89.8% | — |
| LMArena Instruction Following | 1405 | — |
Long Context Not comparable
Gemini 2.5 Flash: 47.5 (#17), Ministral 3B: —
| Benchmark | Gemini 2.5 Flash | Ministral 3B |
|---|---|---|
| Fiction.LiveBench | 77.8% | — |
| LMArena Longer Query | 1419 | — |
Writing & Preference Not comparable
Gemini 2.5 Flash: 53.8 (#157), Ministral 3B: —
| Benchmark | Gemini 2.5 Flash | Ministral 3B |
|---|---|---|
| LMArena Text | 1417 | — |
| LMArena Creative Writing | 1400 | — |
| Short-Story Creative Writing | 76.5% | — |
| EQ-Bench Creative Writing | 1137 | — |
| WildBench | 81.7% | — |
| LMArena Multi-Turn | 1408 | — |
Frequently asked questions
Is Gemini 2.5 Flash better than Ministral 3B?
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 26.2 on the Noometry Index. Ministral 3B costs 8.5× less per token, which makes it the better buy when Gemini 2.5 Flash's lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 Flash or Ministral 3B?
Ministral 3B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Gemini 2.5 Flash lists at $0.30 and $2.50.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 131K.
How many benchmarks do Gemini 2.5 Flash and Ministral 3B share?
4 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Ministral 3B has 6.