Model comparison
Ministral 3B vs Mistral
Mistral is the stronger model overall, scoring 29.4 to 25.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in knowledge, where Mistral leads 16.3 to 10.4.
- Ministral 3B has downloadable open weights; the other is API-only.
Side by side
| Ministral 3B | Mistral | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 25.6 | 29.4 |
| Released | 2024-10-01 | — |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.04 | — |
| Results tracked | 6 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Ministral 3B: —, Mistral: 33.2 (#249)
| Benchmark | Ministral 3B | Mistral |
|---|---|---|
| LMArena Coding | — | 1162 |
Reasoning Mistral leads
Ministral 3B: 17.7 (#278), Mistral: 21.3 (#199)
| Benchmark | Ministral 3B | Mistral |
|---|---|---|
| LMArena Hard Prompts | — | 1149 |
| DTBench | 51.7% | — |
| LMCA | 5.5% | — |
| Epoch Capabilities Index | 118.08 | — |
Math Ministral 3B leads
Ministral 3B: 24.5 (#257), Mistral: 20.5 (#275)
| Benchmark | Ministral 3B | Mistral |
|---|---|---|
| Omni-MATH | — | 7.2% |
| LMArena Math | — | 1180 |
| MATH Level 5 | 14.4% | — |
Knowledge Mistral leads
Ministral 3B: 10.4 (#297), Mistral: 16.3 (#283)
| Benchmark | Ministral 3B | Mistral |
|---|---|---|
| GPQA Diamond | 25.3% | — |
| MMLU-Pro | — | 27.7% |
| Vectara Hallucination Rate | 7.3% | — |
| GPQA (HELM) | — | 30.3% |
| LMArena Expert | — | 1125 |
Multilingual Not comparable
Ministral 3B: —, Mistral: 33.0 (#249)
| Benchmark | Ministral 3B | Mistral |
|---|---|---|
| LMArena Non-English | — | 1129 |
| LMArena Chinese | — | 1109 |
| LMArena French | — | 1179 |
| LMArena German | — | 1155 |
| LMArena Japanese | — | 1012 |
| LMArena Korean | — | 1032 |
| LMArena Russian | — | 1168 |
| LMArena Spanish | — | 1143 |
Instruction Following Not comparable
Ministral 3B: —, Mistral: 52.9 (#283)
| Benchmark | Ministral 3B | Mistral |
|---|---|---|
| IFEval | — | 56.8% |
| LMArena Instruction Following | — | 1152 |
Long Context Not comparable
Ministral 3B: —, Mistral: 35.0 (#240)
| Benchmark | Ministral 3B | Mistral |
|---|---|---|
| LMArena Longer Query | — | 1154 |
Writing & Preference Not comparable
Ministral 3B: —, Mistral: 37.2 (#255)
| Benchmark | Ministral 3B | Mistral |
|---|---|---|
| LMArena Text | — | 1165 |
| LMArena Creative Writing | — | 1158 |
| WildBench | — | 66% |
| LMArena Multi-Turn | — | 1147 |
Frequently asked questions
Is Ministral 3B better than Mistral?
Mistral is the stronger model overall, scoring 29.4 to 25.6 on the Noometry Index.
How many benchmarks do Ministral 3B and Mistral share?
0 benchmarks have published results for both models. Ministral 3B has 6 scored results on Noometry and Mistral has 22.