Model comparison
MiMo-V2.5-Pro vs Qwen2.5-VL 72B Instruct
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 29.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in reasoning, where MiMo-V2.5-Pro leads 26.8 to 20.7.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 131K.
Side by side
| MiMo-V2.5-Pro | Qwen2.5-VL 72B Instruct | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 45.2 | 29.9 |
| Released | 2026-04-22 | 2024-09 |
| Weights | Open | Open |
| Context window | 1.05M | 131K |
| Max output | 131K | 8K |
| Input $ / M tokens | $0.43 | $2.80 |
| Output $ / M tokens | $0.87 | $8.40 |
| Results tracked | 27 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
MiMo-V2.5-Pro: 47.4 (#60), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.5-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena WebDev | 1479 | — |
| SciCode | 50.2% | — |
| LMArena Coding | 1503 | — |
| ALE-Bench | 899.8 | — |
Agentic & Tool Use Not comparable
MiMo-V2.5-Pro: —, Qwen2.5-VL 72B Instruct: 18.6 (#144)
| Benchmark | MiMo-V2.5-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| OSWorld | — | 5% |
Reasoning MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 26.8 (#130), Qwen2.5-VL 72B Instruct: 20.7 (#233)
| Benchmark | MiMo-V2.5-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Kagi LLM Benchmark | — | 36% |
| NYT Connections (extended) | 34.4% | — |
| CritPt | 4% | — |
| LMArena Hard Prompts | 1488 | — |
| DTBench | 84.5% | — |
| LMCA | 29.5% | — |
Math Not comparable
MiMo-V2.5-Pro: 40.0 (#96), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.5-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| ProofBench | 22% | — |
| LMArena Math | 1481 | — |
Knowledge Not comparable
MiMo-V2.5-Pro: 42.2 (#98), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.5-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Expert | 1503 | — |
Multimodal Not comparable
MiMo-V2.5-Pro: —, Qwen2.5-VL 72B Instruct: 33.5 (#97)
| Benchmark | MiMo-V2.5-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Vision | — | 1107 |
| Video-MME | — | 73.5% |
| GeoBench | — | 62% |
| SpatialViz-Bench | — | 33.3% |
Multilingual Not comparable
MiMo-V2.5-Pro: 55.1 (#34), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.5-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Non-English | 1449 | — |
| LMArena Chinese | 1507 | — |
| LMArena French | 1488 | — |
| LMArena German | 1458 | — |
| LMArena Japanese | 1412 | — |
| LMArena Korean | 1437 | — |
| LMArena Russian | 1450 | — |
| LMArena Spanish | 1471 | — |
Instruction Following Not comparable
MiMo-V2.5-Pro: 77.5 (#21), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.5-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1477 | — |
Long Context Not comparable
MiMo-V2.5-Pro: 45.4 (#37), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.5-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1483 | — |
Writing & Preference Not comparable
MiMo-V2.5-Pro: 65.3 (#49), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.5-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Text | 1465 | — |
| LMArena Creative Writing | 1440 | — |
| EQ-Bench Creative Writing | 1493 | — |
| EQ-Bench 4 | 1208 | — |
| LMArena Multi-Turn | 1477 | — |
Frequently asked questions
Is MiMo-V2.5-Pro better than Qwen2.5-VL 72B Instruct?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 29.9 on the Noometry Index.
Which is cheaper, MiMo-V2.5-Pro or Qwen2.5-VL 72B Instruct?
MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Qwen2.5-VL 72B Instruct lists at $2.80 and $8.40.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 131K.
How many benchmarks do MiMo-V2.5-Pro and Qwen2.5-VL 72B Instruct share?
0 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.