Model comparison
MiMo-V2.6-Pro vs Qwen2.5-VL 72B Instruct
MiMo-V2.6-Pro is the stronger model overall, scoring 46.7 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-V2.6-Pro 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-V2.6-Pro leads 30.4 to 20.0.
- MiMo-V2.6-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-V2.6-Pro accepts more context: 1.05M tokens versus 131K.
Side by side
| MiMo-V2.6-Pro | Qwen2.5-VL 72B Instruct | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 46.7 | 29.4 |
| Released | 2026-09-22 | 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 | 14 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
MiMo-V2.6-Pro: 53.2 (#27), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.6-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena WebDev | 1618 | — |
| LMArena Coding | 1538 | — |
Agentic & Tool Use Not comparable
MiMo-V2.6-Pro: —, Qwen2.5-VL 72B Instruct: 18.4 (#136)
| Benchmark | MiMo-V2.6-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| OSWorld | — | 5% |
Reasoning MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 30.4 (#76), Qwen2.5-VL 72B Instruct: 20.0 (#228)
| Benchmark | MiMo-V2.6-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Kagi LLM Benchmark | — | 36% |
| LMArena Hard Prompts | 1511 | — |
Math Not comparable
MiMo-V2.6-Pro: 37.9 (#91), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.6-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Math | 1497 | — |
Knowledge Not comparable
MiMo-V2.6-Pro: 43.0 (#85), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.6-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Expert | 1548 | — |
Multimodal MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 40.2 (#40), Qwen2.5-VL 72B Instruct: 32.9 (#92)
| Benchmark | MiMo-V2.6-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Vision | 1265 | 1107 |
| Video-MME | — | 73.5% |
| GeoBench | — | 62% |
| SpatialViz-Bench | — | 33.3% |
Multilingual Not comparable
MiMo-V2.6-Pro: 57.0 (#15), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.6-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Non-English | 1474 | — |
| LMArena Chinese | 1532 | — |
| LMArena Russian | 1481 | — |
Instruction Following Not comparable
MiMo-V2.6-Pro: 78.2 (#10), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.6-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1490 | — |
Long Context Not comparable
MiMo-V2.6-Pro: 46.0 (#26), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.6-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1500 | — |
Writing & Preference Not comparable
MiMo-V2.6-Pro: 66.9 (#32), Qwen2.5-VL 72B Instruct: —
| Benchmark | MiMo-V2.6-Pro | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Text | 1491 | — |
| LMArena Creative Writing | 1465 | — |
| LMArena Multi-Turn | 1463 | — |
Frequently asked questions
Is MiMo-V2.6-Pro better than Qwen2.5-VL 72B Instruct?
MiMo-V2.6-Pro is the stronger model overall, scoring 46.7 to 29.4 on the Noometry Index.
Which is cheaper, MiMo-V2.6-Pro or Qwen2.5-VL 72B Instruct?
MiMo-V2.6-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-V2.6-Pro does, with 1.05M tokens against 131K.
How many benchmarks do MiMo-V2.6-Pro and Qwen2.5-VL 72B Instruct share?
1 benchmark has published results for both models. MiMo-V2.6-Pro has 14 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.