Model comparison
MiniMax-M3 vs Ministral 3B
MiniMax-M3 is the stronger model overall, scoring 43.5 to 25.6 on the Noometry Index. Ministral 3B costs 13× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
MiniMax
Mistral AISummary
- They share 4 benchmarks with published results for both. MiniMax-M3 scores higher in 3 categories and Ministral 3B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 10.4.
- The biggest single-benchmark swing is GPQA Diamond: 90.9% for MiniMax-M3 and 25.3% for Ministral 3B.
- Ministral 3B is cheaper at $0.04 / $0.04 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
- MiniMax-M3 accepts more context: 1M tokens versus 128K.
Side by side
| MiniMax-M3 | Ministral 3B | |
|---|---|---|
| Provider | MiniMax | Mistral AI |
| Noometry Index | 43.5 | 25.6 |
| Released | 2026-06-01 | 2024-10-01 |
| Weights | Open | Open |
| Context window | 1M | 128K |
| Max output | 512K | 128K |
| Input $ / M tokens | $0.30 | $0.04 |
| Output $ / M tokens | $1.20 | $0.04 |
| Results tracked | 41 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
MiniMax-M3: 41.5 (#111), Ministral 3B: —
| Benchmark | MiniMax-M3 | Ministral 3B |
|---|---|---|
| FrontierCode | 14.7% | — |
| LMArena WebDev | 1482 | — |
| SciCode | 47.1% | — |
| LMArena Coding | 1470 | — |
| ALE-Bench | 640.02 | — |
Agentic & Tool Use Not comparable
MiniMax-M3: 22.5 (#121), Ministral 3B: —
| Benchmark | MiniMax-M3 | Ministral 3B |
|---|---|---|
| APEX-Agents | 37.7% | — |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 2,158 | — |
Reasoning MiniMax-M3 leads
MiniMax-M3: 29.3 (#83), Ministral 3B: 17.7 (#278)
| Benchmark | MiniMax-M3 | Ministral 3B |
|---|---|---|
| DTBench | 78.9% | 51.7% |
| LMCA | 33.7% | 5.5% |
| Epoch Capabilities Index | 147 | 118.08 |
| SimpleBench | 45.8% | — |
| NYT Connections (extended) | 65.1% | — |
| CritPt | 3.7% | — |
| Chess Puzzles | 14% | — |
| LMArena Hard Prompts | 1447 | — |
| Mystery Game Puzzles | 8% | — |
| Surface Evolver Bench | 55% | — |
| ForecastBench | 61.4 | — |
Math MiniMax-M3 leads
MiniMax-M3: 39.1 (#83), Ministral 3B: 24.5 (#257)
| Benchmark | MiniMax-M3 | Ministral 3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 18% | — |
| LMArena Math | 1432 | — |
| MATH Level 5 | — | 14.4% |
Knowledge MiniMax-M3 leads
MiniMax-M3: 58.4 (#32), Ministral 3B: 10.4 (#297)
| Benchmark | MiniMax-M3 | Ministral 3B |
|---|---|---|
| GPQA Diamond | 90.9% | 25.3% |
| Vectara Hallucination Rate | — | 7.3% |
| LMArena Expert | 1462 | — |
Multimodal Not comparable
MiniMax-M3: 39.5 (#45), Ministral 3B: —
| Benchmark | MiniMax-M3 | Ministral 3B |
|---|---|---|
| LMArena Vision | 1254 | — |
| LMArena Document | 1435 | — |
Multilingual Not comparable
MiniMax-M3: 53.2 (#70), Ministral 3B: —
| Benchmark | MiniMax-M3 | Ministral 3B |
|---|---|---|
| LMArena Non-English | 1420 | — |
| LMArena Chinese | 1465 | — |
| LMArena French | 1445 | — |
| LMArena German | 1424 | — |
| LMArena Japanese | 1381 | — |
| LMArena Korean | 1372 | — |
| LMArena Russian | 1430 | — |
| LMArena Spanish | 1431 | — |
Instruction Following Not comparable
MiniMax-M3: 75.7 (#56), Ministral 3B: —
| Benchmark | MiniMax-M3 | Ministral 3B |
|---|---|---|
| LMArena Instruction Following | 1433 | — |
Long Context Not comparable
MiniMax-M3: 44.2 (#68), Ministral 3B: —
| Benchmark | MiniMax-M3 | Ministral 3B |
|---|---|---|
| LMArena Longer Query | 1445 | — |
Writing & Preference Not comparable
MiniMax-M3: 62.3 (#79), Ministral 3B: —
| Benchmark | MiniMax-M3 | Ministral 3B |
|---|---|---|
| LMArena Text | 1433 | — |
| LMArena Creative Writing | 1405 | — |
| EQ-Bench 4 | 1150 | — |
| LMArena Multi-Turn | 1441 | — |
Frequently asked questions
Is MiniMax-M3 better than Ministral 3B?
MiniMax-M3 is the stronger model overall, scoring 43.5 to 25.6 on the Noometry Index. Ministral 3B costs 13× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.
Which is cheaper, MiniMax-M3 or Ministral 3B?
Ministral 3B is cheaper. It lists at $0.04 per million input tokens and $0.04 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.
Which has the bigger context window?
MiniMax-M3 does, with 1M tokens against 128K.
How many benchmarks do MiniMax-M3 and Ministral 3B share?
4 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Ministral 3B has 6.