Model comparison
MiMo-V2-Pro vs Qwen2.5 7B Instruct
MiMo-V2-Pro is the stronger model overall, scoring 42.4 to 28.6 on the Noometry Index. Qwen2.5 7B Instruct costs 1.8× less per token, which makes it the better buy when MiMo-V2-Pro's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in math, where MiMo-V2-Pro leads 36.7 to 11.8.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2-Pro.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 131K.
- Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2-Pro | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 42.4 | 28.6 |
| Released | 2026-03-18 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 131K | 8K |
| Input $ / M tokens | $0.43 | $0.17 |
| Output $ / M tokens | $0.87 | $0.70 |
| Results tracked | 23 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Pro leads
MiMo-V2-Pro: 43.4 (#76), Qwen2.5 7B Instruct: 35.9 (#204)
| Benchmark | MiMo-V2-Pro | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena WebDev | 1433 | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1476 | — |
| BigCodeBench Complete | — | 46.1% |
| ALE-Bench | 785.17 | — |
Agentic & Tool Use Not comparable
MiMo-V2-Pro: —, Qwen2.5 7B Instruct: 23.5 (#117)
| Benchmark | MiMo-V2-Pro | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |
Reasoning MiMo-V2-Pro leads
MiMo-V2-Pro: 21.3 (#200), Qwen2.5 7B Instruct: 14.3 (#317)
| Benchmark | MiMo-V2-Pro | Qwen2.5 7B Instruct |
|---|---|---|
| NYT Connections (extended) | 25.8% | — |
| Chess Puzzles | — | 0% |
| Thematic Generalization | 45.9% | — |
| LMArena Hard Prompts | 1457 | — |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |
| Epoch Capabilities Index | — | 118.44 |
Math MiMo-V2-Pro leads
MiMo-V2-Pro: 36.7 (#104), Qwen2.5 7B Instruct: 11.8 (#300)
| Benchmark | MiMo-V2-Pro | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.5% |
| Omni-MATH | — | 29.4% |
| LMArena Math | 1447 | — |
Knowledge MiMo-V2-Pro leads
MiMo-V2-Pro: 40.8 (#106), Qwen2.5 7B Instruct: 17.0 (#281)
| Benchmark | MiMo-V2-Pro | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | — | 35.5% |
| MMLU-Pro | — | 53.9% |
| GPQA (HELM) | — | 34.1% |
| LMArena Expert | 1479 | — |
| MMLU | — | 72.9% |
Multilingual Not comparable
MiMo-V2-Pro: 52.9 (#77), Qwen2.5 7B Instruct: —
| Benchmark | MiMo-V2-Pro | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1416 | — |
| LMArena Chinese | 1455 | — |
| LMArena French | 1470 | — |
| LMArena German | 1417 | — |
| LMArena Japanese | 1366 | — |
| LMArena Korean | 1401 | — |
| LMArena Russian | 1427 | — |
| LMArena Spanish | 1458 | — |
Instruction Following MiMo-V2-Pro leads
MiMo-V2-Pro: 76.2 (#46), Qwen2.5 7B Instruct: 63.4 (#226)
| Benchmark | MiMo-V2-Pro | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1444 | — |
Long Context Not comparable
MiMo-V2-Pro: 41.5 (#133), Qwen2.5 7B Instruct: —
| Benchmark | MiMo-V2-Pro | Qwen2.5 7B Instruct |
|---|---|---|
| CL-bench | 15.7% | — |
| CL-bench Life | 6.9% | — |
| LMArena Longer Query | 1455 | — |
Writing & Preference MiMo-V2-Pro leads
MiMo-V2-Pro: 62.9 (#67), Qwen2.5 7B Instruct: 48.8 (#194)
| Benchmark | MiMo-V2-Pro | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1436 | — |
| LMArena Creative Writing | 1415 | — |
| WildBench | — | 73.1% |
| LMArena Multi-Turn | 1456 | — |
Frequently asked questions
Is MiMo-V2-Pro better than Qwen2.5 7B Instruct?
MiMo-V2-Pro is the stronger model overall, scoring 42.4 to 28.6 on the Noometry Index. Qwen2.5 7B Instruct costs 1.8× less per token, which makes it the better buy when MiMo-V2-Pro's lead doesn't matter for your workload.
Which is cheaper, MiMo-V2-Pro or Qwen2.5 7B Instruct?
Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; MiMo-V2-Pro lists at $0.43 and $0.87.
Is MiMo-V2-Pro or Qwen2.5 7B Instruct better for coding?
MiMo-V2-Pro scores higher on coding benchmarks: 43.4 versus 35.9 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2-Pro does, with 1.05M tokens against 131K.
How many benchmarks do MiMo-V2-Pro and Qwen2.5 7B Instruct share?
0 benchmarks have published results for both models. MiMo-V2-Pro has 23 scored results on Noometry and Qwen2.5 7B Instruct has 15.