Model comparison
MiMo-V2.5-Pro vs MiniMax-M2.5
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 38.1 on the Noometry Index.
Last verified . 22 shared benchmarks.
MiniMaxSummary
- They share 22 benchmarks with published results for both. MiMo-V2.5-Pro scores higher in 7 categories and MiniMax-M2.5 in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.5-Pro leads 38.6 to 25.8.
- The biggest single-benchmark swing is ProofBench: 22% for MiMo-V2.5-Pro and 4% for MiniMax-M2.5.
- Both cost about the same: $0.43 input and $0.87 output per million tokens.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 205K.
Side by side
| MiMo-V2.5-Pro | MiniMax-M2.5 | |
|---|---|---|
| Provider | Xiaomi | MiniMax |
| Noometry Index | 44.8 | 38.1 |
| Released | 2026-04-22 | 2026-02-12 |
| Weights | Open | Open |
| Context window | 1.05M | 205K |
| Max output | 131K | 131K |
| Input $ / M tokens | $0.43 | $0.30 |
| Output $ / M tokens | $0.87 | $1.20 |
| Results tracked | 27 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
MiMo-V2.5-Pro: 47.0 (#58), MiniMax-M2.5: 47.9 (#53)
| Benchmark | MiMo-V2.5-Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena WebDev | 1477 | 1386 |
| LMArena Coding | 1502 | 1380 |
| ALE-Bench | 899.8 | 618.17 |
| SWE-bench Verified (bash only) | — | 75.8% |
| SWE-bench Multilingual | — | 68.3% |
| SciCode | 50.2% | — |
Agentic & Tool Use Not comparable
MiMo-V2.5-Pro: —, MiniMax-M2.5: 30.2 (#70)
| Benchmark | MiMo-V2.5-Pro | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| Vending-Bench 2 | — | -23.16 |
Reasoning MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 25.9 (#124), MiniMax-M2.5: 17.6 (#281)
| Benchmark | MiMo-V2.5-Pro | MiniMax-M2.5 |
|---|---|---|
| NYT Connections (extended) | 34.4% | 16.8% |
| LMArena Hard Prompts | 1487 | 1372 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 55.2% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | 4% | — |
| DTBench | 84.5% | — |
| LMCA | 29.5% | — |
| Epoch Capabilities Index | — | 146.68 |
Math MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 38.6 (#84), MiniMax-M2.5: 25.8 (#242)
| Benchmark | MiMo-V2.5-Pro | MiniMax-M2.5 |
|---|---|---|
| ProofBench | 22% | 4% |
| LMArena Math | 1480 | 1378 |
Knowledge MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 41.5 (#100), MiniMax-M2.5: 38.6 (#132)
| Benchmark | MiMo-V2.5-Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1501 | 1378 |
| Vectara Hallucination Rate | — | 9.1% |
Multilingual MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 55.3 (#33), MiniMax-M2.5: 47.3 (#147)
| Benchmark | MiMo-V2.5-Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1449 | 1338 |
| LMArena Chinese | 1507 | 1392 |
| LMArena French | 1489 | 1363 |
| LMArena German | 1455 | 1361 |
| LMArena Japanese | 1418 | 1169 |
| LMArena Korean | 1436 | 1232 |
| LMArena Russian | 1450 | 1359 |
| LMArena Spanish | 1470 | 1354 |
Instruction Following MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 77.6 (#21), MiniMax-M2.5: 71.7 (#143)
| Benchmark | MiMo-V2.5-Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1477 | 1353 |
Long Context MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 45.4 (#38), MiniMax-M2.5: 37.4 (#211)
| Benchmark | MiMo-V2.5-Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1482 | 1367 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 65.5 (#47), MiniMax-M2.5: 54.1 (#149)
| Benchmark | MiMo-V2.5-Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1465 | 1359 |
| LMArena Creative Writing | 1440 | 1331 |
| EQ-Bench Creative Writing | 1493 | 1361 |
| LMArena Multi-Turn | 1477 | 1364 |
| EQ-Bench 4 | 1208 | — |
Frequently asked questions
Is MiMo-V2.5-Pro better than MiniMax-M2.5?
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 38.1 on the Noometry Index.
Which is cheaper, MiMo-V2.5-Pro or MiniMax-M2.5?
MiniMax-M2.5 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; MiMo-V2.5-Pro lists at $0.43 and $0.87.
Is MiMo-V2.5-Pro or MiniMax-M2.5 better for coding?
They score almost the same on coding (47.0 vs 47.9); test both on your own repository before choosing.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 205K.
How many benchmarks do MiMo-V2.5-Pro and MiniMax-M2.5 share?
22 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and MiniMax-M2.5 has 33.