Model comparison
MiMo-V2.6-Pro vs Ministral 3 8B 2512 (batch)
MiMo-V2.6-Pro has enough public results to be ranked (#55); Ministral 3 8B 2512 (batch) does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in knowledge, where MiMo-V2.6-Pro leads 43.0 to 26.6.
- Ministral 3 8B 2512 (batch) is cheaper at $0.075 / $0.075 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.6-Pro.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 128K.
Side by side
| MiMo-V2.6-Pro | Ministral 3 8B 2512 (batch) | |
|---|---|---|
| Provider | Xiaomi | Mistral AI |
| Noometry Index | 46.7 | 32.3 |
| Released | 2026-09-22 | 2025-12-02 |
| Weights | Open | Open |
| Context window | 1.05M | 128K |
| Max output | 131K | 4K |
| Input $ / M tokens | $0.43 | $0.075 |
| Output $ / M tokens | $0.87 | $0.075 |
| Results tracked | 14 | 1 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
MiMo-V2.6-Pro: 53.2 (#27), Ministral 3 8B 2512 (batch): —
| Benchmark | MiMo-V2.6-Pro | Ministral 3 8B 2512 (batch) |
|---|---|---|
| LMArena WebDev | 1618 | — |
| LMArena Coding | 1538 | — |
Reasoning Not comparable
MiMo-V2.6-Pro: 30.4 (#76), Ministral 3 8B 2512 (batch): —
| Benchmark | MiMo-V2.6-Pro | Ministral 3 8B 2512 (batch) |
|---|---|---|
| LMArena Hard Prompts | 1511 | — |
Math Not comparable
MiMo-V2.6-Pro: 37.9 (#91), Ministral 3 8B 2512 (batch): —
| Benchmark | MiMo-V2.6-Pro | Ministral 3 8B 2512 (batch) |
|---|---|---|
| LMArena Math | 1497 | — |
Knowledge MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 43.0 (#85), Ministral 3 8B 2512 (batch): 26.6
| Benchmark | MiMo-V2.6-Pro | Ministral 3 8B 2512 (batch) |
|---|---|---|
| Vectara Hallucination Rate | — | 21.7% |
| LMArena Expert | 1548 | — |
Multimodal Not comparable
MiMo-V2.6-Pro: 40.2 (#40), Ministral 3 8B 2512 (batch): —
| Benchmark | MiMo-V2.6-Pro | Ministral 3 8B 2512 (batch) |
|---|---|---|
| LMArena Vision | 1265 | — |
Multilingual Not comparable
MiMo-V2.6-Pro: 57.0 (#15), Ministral 3 8B 2512 (batch): —
| Benchmark | MiMo-V2.6-Pro | Ministral 3 8B 2512 (batch) |
|---|---|---|
| LMArena Non-English | 1474 | — |
| LMArena Chinese | 1532 | — |
| LMArena Russian | 1481 | — |
Instruction Following Not comparable
MiMo-V2.6-Pro: 78.2 (#10), Ministral 3 8B 2512 (batch): —
| Benchmark | MiMo-V2.6-Pro | Ministral 3 8B 2512 (batch) |
|---|---|---|
| LMArena Instruction Following | 1490 | — |
Long Context Not comparable
MiMo-V2.6-Pro: 46.0 (#26), Ministral 3 8B 2512 (batch): —
| Benchmark | MiMo-V2.6-Pro | Ministral 3 8B 2512 (batch) |
|---|---|---|
| LMArena Longer Query | 1500 | — |
Writing & Preference Not comparable
MiMo-V2.6-Pro: 66.9 (#32), Ministral 3 8B 2512 (batch): —
| Benchmark | MiMo-V2.6-Pro | Ministral 3 8B 2512 (batch) |
|---|---|---|
| LMArena Text | 1491 | — |
| LMArena Creative Writing | 1465 | — |
| LMArena Multi-Turn | 1463 | — |
Frequently asked questions
Is MiMo-V2.6-Pro better than Ministral 3 8B 2512 (batch)?
MiMo-V2.6-Pro has enough public results to be ranked (#55); Ministral 3 8B 2512 (batch) does not yet, so treat this comparison as directional.
Which is cheaper, MiMo-V2.6-Pro or Ministral 3 8B 2512 (batch)?
Ministral 3 8B 2512 (batch) is cheaper. It lists at $0.075 per million input tokens and $0.075 per million output tokens; MiMo-V2.6-Pro lists at $0.43 and $0.87.
Which has the bigger context window?
MiMo-V2.6-Pro does, with 1.05M tokens against 128K.
How many benchmarks do MiMo-V2.6-Pro and Ministral 3 8B 2512 (batch) share?
0 benchmarks have published results for both models. MiMo-V2.6-Pro has 14 scored results on Noometry and Ministral 3 8B 2512 (batch) has 1.