Model comparison
MiMo-V2.5-Pro vs Qwen2.5 32B Instruct
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 29.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in math, where MiMo-V2.5-Pro leads 38.6 to 15.3.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $0.70 / $2.80 for Qwen2.5 32B Instruct.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 131K.
Side by side
| MiMo-V2.5-Pro | Qwen2.5 32B Instruct | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 44.8 | 29.7 |
| Released | 2026-04-22 | 2024-09 |
| Weights | Open | Open |
| Context window | 1.05M | 131K |
| Max output | 131K | 8K |
| Input $ / M tokens | $0.43 | $0.70 |
| Output $ / M tokens | $0.87 | $2.80 |
| Results tracked | 27 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 47.0 (#58), Qwen2.5 32B Instruct: 38.1 (#165)
| Benchmark | MiMo-V2.5-Pro | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena WebDev | 1477 | — |
| SciCode | 50.2% | — |
| BigCodeBench Instruct | — | 45% |
| LMArena Coding | 1502 | — |
| BigCodeBench Complete | — | 52.3% |
| ALE-Bench | 899.8 | — |
Reasoning MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 25.9 (#124), Qwen2.5 32B Instruct: 18.5 (#262)
| Benchmark | MiMo-V2.5-Pro | Qwen2.5 32B Instruct |
|---|---|---|
| NYT Connections (extended) | 34.4% | — |
| CritPt | 4% | — |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1487 | — |
| DTBench | 84.5% | — |
| LMCA | 29.5% | — |
| Epoch Capabilities Index | — | 128.52 |
Math MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 38.6 (#84), Qwen2.5 32B Instruct: 15.3 (#289)
| Benchmark | MiMo-V2.5-Pro | Qwen2.5 32B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 7.4% |
| ProofBench | 22% | — |
| LMArena Math | 1480 | — |
| MATH Level 5 | — | 56.1% |
Knowledge MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 41.5 (#100), Qwen2.5 32B Instruct: 24.9 (#259)
| Benchmark | MiMo-V2.5-Pro | Qwen2.5 32B Instruct |
|---|---|---|
| GPQA Diamond | — | 46.1% |
| LMArena Expert | 1501 | — |
Multilingual Not comparable
MiMo-V2.5-Pro: 55.3 (#33), Qwen2.5 32B Instruct: —
| Benchmark | MiMo-V2.5-Pro | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Non-English | 1449 | — |
| LMArena Chinese | 1507 | — |
| LMArena French | 1489 | — |
| LMArena German | 1455 | — |
| LMArena Japanese | 1418 | — |
| LMArena Korean | 1436 | — |
| LMArena Russian | 1450 | — |
| LMArena Spanish | 1470 | — |
Instruction Following Not comparable
MiMo-V2.5-Pro: 77.6 (#21), Qwen2.5 32B Instruct: —
| Benchmark | MiMo-V2.5-Pro | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Instruction Following | 1477 | — |
Long Context Not comparable
MiMo-V2.5-Pro: 45.4 (#38), Qwen2.5 32B Instruct: —
| Benchmark | MiMo-V2.5-Pro | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Longer Query | 1482 | — |
Writing & Preference Not comparable
MiMo-V2.5-Pro: 65.5 (#47), Qwen2.5 32B Instruct: —
| Benchmark | MiMo-V2.5-Pro | Qwen2.5 32B 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 32B Instruct?
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 29.7 on the Noometry Index.
Which is cheaper, MiMo-V2.5-Pro or Qwen2.5 32B 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 32B Instruct lists at $0.70 and $2.80.
Is MiMo-V2.5-Pro or Qwen2.5 32B Instruct better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.0 versus 38.1 in the Noometry coding category.
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 32B Instruct share?
0 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and Qwen2.5 32B Instruct has 7.