Model comparison
MiMo-V2-Flash vs MiniMax-M3
MiniMax-M3 is the stronger model overall, scoring 43.5 to 40.8 on the Noometry Index. MiMo-V2-Flash costs 3.0× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
MiniMaxSummary
- They share 21 benchmarks with published results for both. MiMo-V2-Flash scores higher in 0 categories and MiniMax-M3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 39.1.
- The biggest single-benchmark swing is SciCode: 25.9% for MiMo-V2-Flash and 47.1% for MiniMax-M3.
- MiMo-V2-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
- MiniMax-M3 accepts more context: 1M tokens versus 262K.
Side by side
| MiMo-V2-Flash | MiniMax-M3 | |
|---|---|---|
| Provider | Xiaomi | MiniMax |
| Noometry Index | 40.8 | 43.5 |
| Released | 2025-12-16 | 2026-06-01 |
| Weights | Open | Open |
| Context window | 262K | 1M |
| Max output | 66K | 512K |
| Input $ / M tokens | $0.14 | $0.30 |
| Output $ / M tokens | $0.28 | $1.20 |
| Results tracked | 21 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
MiMo-V2-Flash: 35.8 (#205), MiniMax-M3: 41.5 (#111)
| Benchmark | MiMo-V2-Flash | MiniMax-M3 |
|---|---|---|
| LMArena WebDev | 1330 | 1482 |
| SciCode | 25.9% | 47.1% |
| LMArena Coding | 1443 | 1470 |
| ALE-Bench | 737.95 | 640.02 |
| FrontierCode | — | 14.7% |
Agentic & Tool Use Not comparable
MiMo-V2-Flash: —, MiniMax-M3: 22.5 (#121)
| Benchmark | MiMo-V2-Flash | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |
Reasoning MiniMax-M3 leads
MiMo-V2-Flash: 24.1 (#155), MiniMax-M3: 29.3 (#83)
| Benchmark | MiMo-V2-Flash | MiniMax-M3 |
|---|---|---|
| CritPt | 0% | 3.7% |
| LMArena Hard Prompts | 1420 | 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 | — | 147 |
| ForecastBench | — | 61.4 |
Math MiniMax-M3 leads
MiMo-V2-Flash: 35.6 (#141), MiniMax-M3: 39.1 (#83)
| Benchmark | MiMo-V2-Flash | MiniMax-M3 |
|---|---|---|
| LMArena Math | 1396 | 1432 |
| OTIS Mock AIME 2024-2025 | — | 71.1% |
| ProofBench | — | 18% |
Knowledge MiniMax-M3 leads
MiMo-V2-Flash: 39.1 (#126), MiniMax-M3: 58.4 (#32)
| Benchmark | MiMo-V2-Flash | MiniMax-M3 |
|---|---|---|
| LMArena Expert | 1425 | 1462 |
| GPQA Diamond | — | 90.9% |
Multimodal Not comparable
MiMo-V2-Flash: —, MiniMax-M3: 39.5 (#45)
| Benchmark | MiMo-V2-Flash | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1254 |
| LMArena Document | — | 1435 |
Multilingual MiniMax-M3 leads
MiMo-V2-Flash: 51.1 (#109), MiniMax-M3: 53.2 (#70)
| Benchmark | MiMo-V2-Flash | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1391 | 1420 |
| LMArena Chinese | 1463 | 1465 |
| LMArena French | 1429 | 1445 |
| LMArena German | 1395 | 1424 |
| LMArena Japanese | 1324 | 1381 |
| LMArena Korean | 1358 | 1372 |
| LMArena Russian | 1387 | 1430 |
| LMArena Spanish | 1420 | 1431 |
Instruction Following MiniMax-M3 leads
MiMo-V2-Flash: 73.7 (#115), MiniMax-M3: 75.7 (#56)
| Benchmark | MiMo-V2-Flash | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1392 | 1433 |
Long Context MiniMax-M3 leads
MiMo-V2-Flash: 43.0 (#106), MiniMax-M3: 44.2 (#68)
| Benchmark | MiMo-V2-Flash | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1409 | 1445 |
Writing & Preference MiniMax-M3 leads
MiMo-V2-Flash: 59.9 (#101), MiniMax-M3: 62.3 (#79)
| Benchmark | MiMo-V2-Flash | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1411 | 1433 |
| LMArena Creative Writing | 1375 | 1405 |
| LMArena Multi-Turn | 1404 | 1441 |
| EQ-Bench 4 | — | 1150 |
Frequently asked questions
Is MiMo-V2-Flash better than MiniMax-M3?
MiniMax-M3 is the stronger model overall, scoring 43.5 to 40.8 on the Noometry Index. MiMo-V2-Flash costs 3.0× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.
Which is cheaper, MiMo-V2-Flash or MiniMax-M3?
MiMo-V2-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.
Is MiMo-V2-Flash or MiniMax-M3 better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.5 versus 35.8 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M3 does, with 1M tokens against 262K.
How many benchmarks do MiMo-V2-Flash and MiniMax-M3 share?
21 benchmarks have published results for both models. MiMo-V2-Flash has 21 scored results on Noometry and MiniMax-M3 has 41.