Model comparison
MiMo-V2.5 vs MiniMax-M2.5
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 38.3 on the Noometry Index.
Last verified . 20 shared benchmarks.
MiniMaxSummary
- They share 20 benchmarks with published results for both. MiMo-V2.5 scores higher in 7 categories and MiniMax-M2.5 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.5 leads 28.6 to 17.5.
- The biggest single-benchmark swing is ProofBench: 16% for MiMo-V2.5 and 4% for MiniMax-M2.5.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.5.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 205K.
Side by side
| MiMo-V2.5 | MiniMax-M2.5 | |
|---|---|---|
| Provider | Xiaomi | MiniMax |
| Noometry Index | 43.4 | 38.3 |
| Released | 2026-04-22 | 2026-02-12 |
| Weights | Open | Open |
| Context window | 1.05M | 205K |
| Max output | 131K | 131K |
| Input $ / M tokens | $0.14 | $0.30 |
| Output $ / M tokens | $0.28 | $1.20 |
| Results tracked | 23 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
MiMo-V2.5: 43.9 (#81), MiniMax-M2.5: 48.1 (#58)
| Benchmark | MiMo-V2.5 | MiniMax-M2.5 |
|---|---|---|
| LMArena WebDev | 1438 | 1387 |
| LMArena Coding | 1469 | 1381 |
| ALE-Bench | 513.95 | 618.17 |
| SWE-bench Verified (bash only) | — | 75.8% |
| SWE-bench Multilingual | — | 68.3% |
| SciCode | 43.1% | — |
Agentic & Tool Use Not comparable
MiMo-V2.5: —, MiniMax-M2.5: 30.4 (#77)
| Benchmark | MiMo-V2.5 | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| Vending-Bench 2 | — | -23.16 |
Reasoning MiMo-V2.5 leads
MiMo-V2.5: 28.6 (#101), MiniMax-M2.5: 17.5 (#292)
| Benchmark | MiMo-V2.5 | MiniMax-M2.5 |
|---|---|---|
| LMArena Hard Prompts | 1450 | 1372 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 55.2% |
| NYT Connections (extended) | — | 16.8% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | 3.7% | — |
| Epoch Capabilities Index | — | 146.68 |
Math MiMo-V2.5 leads
MiMo-V2.5: 36.8 (#163), MiniMax-M2.5: 26.9 (#253)
| Benchmark | MiMo-V2.5 | MiniMax-M2.5 |
|---|---|---|
| ProofBench | 16% | 4% |
| LMArena Math | 1436 | 1378 |
Knowledge MiMo-V2.5 leads
MiMo-V2.5: 40.8 (#115), MiniMax-M2.5: 39.2 (#135)
| Benchmark | MiMo-V2.5 | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1460 | 1379 |
| Vectara Hallucination Rate | — | 9.1% |
Multimodal Not comparable
MiMo-V2.5: 39.8 (#54), MiniMax-M2.5: —
| Benchmark | MiMo-V2.5 | MiniMax-M2.5 |
|---|---|---|
| LMArena Vision | 1247 | — |
Multilingual MiMo-V2.5 leads
MiMo-V2.5: 51.9 (#99), MiniMax-M2.5: 47.1 (#152)
| Benchmark | MiMo-V2.5 | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1404 | 1338 |
| LMArena Chinese | 1468 | 1393 |
| LMArena French | 1447 | 1362 |
| LMArena German | 1421 | 1362 |
| LMArena Japanese | 1306 | 1171 |
| LMArena Korean | 1363 | 1232 |
| LMArena Russian | 1395 | 1358 |
| LMArena Spanish | 1416 | 1354 |
Instruction Following MiMo-V2.5 leads
MiMo-V2.5: 75.5 (#60), MiniMax-M2.5: 71.5 (#148)
| Benchmark | MiMo-V2.5 | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1434 | 1353 |
Long Context MiMo-V2.5 leads
MiMo-V2.5: 44.2 (#73), MiniMax-M2.5: 37.5 (#216)
| Benchmark | MiMo-V2.5 | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1445 | 1366 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference MiMo-V2.5 leads
MiMo-V2.5: 61.6 (#86), MiniMax-M2.5: 53.9 (#153)
| Benchmark | MiMo-V2.5 | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1428 | 1359 |
| LMArena Creative Writing | 1393 | 1331 |
| LMArena Multi-Turn | 1445 | 1364 |
| EQ-Bench Creative Writing | — | 1361 |
Frequently asked questions
Is MiMo-V2.5 better than MiniMax-M2.5?
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 38.3 on the Noometry Index.
Which is cheaper, MiMo-V2.5 or MiniMax-M2.5?
MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; MiniMax-M2.5 lists at $0.30 and $1.20.
Is MiMo-V2.5 or MiniMax-M2.5 better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 43.9 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 205K.
How many benchmarks do MiMo-V2.5 and MiniMax-M2.5 share?
20 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and MiniMax-M2.5 has 33.