Model comparison
MiMo-V2.5 vs Qwen2.5-VL 72B Instruct
MiMo-V2.5 is the stronger model overall, scoring 43.0 to 29.4 on the Noometry Index.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. MiMo-V2.5 scores higher in 2 categories and Qwen2.5-VL 72B Instruct in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.5 leads 27.8 to 20.0.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 131K.
Side by side
| MiMo-V2.5 | Qwen2.5-VL 72B Instruct | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 43.0 | 29.4 |
| Released | 2026-04-22 | 2024-09 |
| Weights | Open | Open |
| Context window | 1.05M | 131K |
| Max output | 131K | 8K |
| Input $ / M tokens | $0.14 | $2.80 |
| Output $ / M tokens | $0.28 | $8.40 |
| Results tracked | 23 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
MiMo-V2.5: 43.6 (#75), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena WebDev | 1438 | — |
| SciCode | 43.1% | — |
| LMArena Coding | 1469 | — |
| ALE-Bench | 513.95 | — |
Agentic & Tool Use Not comparable
MiMo-V2.5: —, Qwen2.5-VL 72B Instruct: 18.4 (#136)
| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| OSWorld | — | 5% |
Reasoning MiMo-V2.5 leads
MiMo-V2.5: 27.8 (#98), Qwen2.5-VL 72B Instruct: 20.0 (#228)
| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Kagi LLM Benchmark | — | 36% |
| CritPt | 3.7% | — |
| LMArena Hard Prompts | 1450 | — |
Math Not comparable
MiMo-V2.5: 35.4 (#145), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| ProofBench | 16% | — |
| LMArena Math | 1436 | — |
Knowledge Not comparable
MiMo-V2.5: 40.2 (#109), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Expert | 1459 | — |
Multimodal MiMo-V2.5 leads
MiMo-V2.5: 39.0 (#53), Qwen2.5-VL 72B Instruct: 32.9 (#92)
| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Vision | 1245 | 1107 |
| Video-MME | — | 73.5% |
| GeoBench | — | 62% |
| SpatialViz-Bench | — | 33.3% |
Multilingual Not comparable
MiMo-V2.5: 52.0 (#96), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Non-English | 1404 | — |
| LMArena Chinese | 1467 | — |
| LMArena French | 1447 | — |
| LMArena German | 1421 | — |
| LMArena Japanese | 1304 | — |
| LMArena Korean | 1363 | — |
| LMArena Russian | 1395 | — |
| LMArena Spanish | 1412 | — |
Instruction Following Not comparable
MiMo-V2.5: 75.7 (#55), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1433 | — |
Long Context Not comparable
MiMo-V2.5: 44.1 (#69), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1444 | — |
Writing & Preference Not comparable
MiMo-V2.5: 61.8 (#82), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Text | 1427 | — |
| LMArena Creative Writing | 1392 | — |
| LMArena Multi-Turn | 1445 | — |
Frequently asked questions
Is MiMo-V2.5 better than Qwen2.5-VL 72B Instruct?
MiMo-V2.5 is the stronger model overall, scoring 43.0 to 29.4 on the Noometry Index.
Which is cheaper, MiMo-V2.5 or Qwen2.5-VL 72B Instruct?
MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 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 does, with 1.05M tokens against 131K.
How many benchmarks do MiMo-V2.5 and Qwen2.5-VL 72B Instruct share?
1 benchmark has published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.