Model comparison
MiMo-V2.6-Pro vs MiniMax-M3
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 43.8 on the Noometry Index.
Last verified . 19 shared benchmarks.
MiniMaxSummary
- They share 19 benchmarks with published results for both. MiMo-V2.6-Pro scores higher in 9 categories and MiniMax-M3 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where MiMo-V2.6-Pro leads 37.5 to 22.6.
- The biggest single-benchmark swing is ProofBench: 70% for MiMo-V2.6-Pro and 18% for MiniMax-M3.
- Both cost about the same: $0.43 input and $0.87 output per million tokens.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 1M.
Side by side
| MiMo-V2.6-Pro | MiniMax-M3 | |
|---|---|---|
| Provider | Xiaomi | MiniMax |
| Noometry Index | 50.3 | 43.8 |
| Released | 2026-09-21 | 2026-06-01 |
| Weights | Open | Open |
| Context window | 1.05M | 1M |
| Max output | 131K | 512K |
| Input $ / M tokens | $0.43 | $0.30 |
| Output $ / M tokens | $0.87 | $1.20 |
| Results tracked | 19 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 55.5 (#23), MiniMax-M3: 41.8 (#118)
| Benchmark | MiMo-V2.6-Pro | MiniMax-M3 |
|---|---|---|
| LMArena WebDev | 1629 | 1482 |
| SciCode | 60.9% | 47.1% |
| LMArena Coding | 1534 | 1469 |
| ALE-Bench | 1,158 | 640.02 |
| FrontierCode | — | 14.7% |
Agentic & Tool Use MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 37.5 (#35), MiniMax-M3: 22.6 (#130)
| Benchmark | MiMo-V2.6-Pro | MiniMax-M3 |
|---|---|---|
| APEX-Agents | 59.5% | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |
Reasoning MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 43.1 (#50), MiniMax-M3: 30.1 (#87)
| Benchmark | MiMo-V2.6-Pro | MiniMax-M3 |
|---|---|---|
| CritPt | 26.6% | 3.7% |
| LMArena Hard Prompts | 1512 | 1447 |
| SimpleBench | — | 45.8% |
| NYT Connections (extended) | — | 65.1% |
| Chess Puzzles | — | 14% |
| Mystery Game Puzzles | — | 8% |
| DTBench | — | 78.9% |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| Epoch Capabilities Index | — | 146.95 |
| ForecastBench | — | 61.4 |
Math MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 54.5 (#45), MiniMax-M3: 40.0 (#95)
| Benchmark | MiMo-V2.6-Pro | MiniMax-M3 |
|---|---|---|
| ProofBench | 70% | 18% |
| LMArena Math | 1494 | 1429 |
| OTIS Mock AIME 2024-2025 | — | 71.1% |
Knowledge MiniMax-M3 leads
MiMo-V2.6-Pro: 43.5 (#92), MiniMax-M3: 58.4 (#35)
| Benchmark | MiMo-V2.6-Pro | MiniMax-M3 |
|---|---|---|
| LMArena Expert | 1543 | 1461 |
| GPQA Diamond | — | 90.9% |
Multimodal Too close to call
MiMo-V2.6-Pro: 40.8 (#43), MiniMax-M3: 40.2 (#51)
| Benchmark | MiMo-V2.6-Pro | MiniMax-M3 |
|---|---|---|
| LMArena Vision | 1264 | 1253 |
| LMArena Document | — | 1435 |
Multilingual MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 56.9 (#14), MiniMax-M3: 53.0 (#75)
| Benchmark | MiMo-V2.6-Pro | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1474 | 1420 |
| LMArena Chinese | 1529 | 1463 |
| LMArena Russian | 1480 | 1428 |
| LMArena French | — | 1447 |
| LMArena German | — | 1426 |
| LMArena Japanese | — | 1381 |
| LMArena Korean | — | 1372 |
| LMArena Spanish | — | 1432 |
Instruction Following MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 78.2 (#12), MiniMax-M3: 75.5 (#62)
| Benchmark | MiMo-V2.6-Pro | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1493 | 1433 |
Long Context MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 46.0 (#27), MiniMax-M3: 44.2 (#72)
| Benchmark | MiMo-V2.6-Pro | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1501 | 1445 |
Writing & Preference MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 66.8 (#33), MiniMax-M3: 62.1 (#83)
| Benchmark | MiMo-V2.6-Pro | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1492 | 1433 |
| LMArena Creative Writing | 1468 | 1404 |
| LMArena Multi-Turn | 1464 | 1442 |
| EQ-Bench 4 | — | 1150 |
Frequently asked questions
Is MiMo-V2.6-Pro better than MiniMax-M3?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 43.8 on the Noometry Index.
Which is cheaper, MiMo-V2.6-Pro or MiniMax-M3?
MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; MiMo-V2.6-Pro lists at $0.43 and $0.87.
Is MiMo-V2.6-Pro or MiniMax-M3 better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 41.8 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Pro does, with 1.05M tokens against 1M.
How many benchmarks do MiMo-V2.6-Pro and MiniMax-M3 share?
19 benchmarks have published results for both models. MiMo-V2.6-Pro has 19 scored results on Noometry and MiniMax-M3 has 41.