Model comparison
MiMo-V2-Pro vs Qwen1.5-14B
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 32.7 on the Noometry Index.
Last verified . 16 shared benchmarks.
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. MiMo-V2-Pro scores higher in 8 categories and Qwen1.5-14B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2-Pro leads 62.8 to 33.6.
- Qwen1.5-14B has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2-Pro | Qwen1.5-14B | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 43.0 | 32.7 |
| Released | 2026-03-18 | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.43 | — |
| Output $ / M tokens | $0.87 | — |
| Results tracked | 23 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Pro leads
MiMo-V2-Pro: 43.8 (#83), Qwen1.5-14B: 33.1 (#263)
| Benchmark | MiMo-V2-Pro | Qwen1.5-14B |
|---|---|---|
| LMArena Coding | 1476 | 1138 |
| LMArena WebDev | 1433 | — |
| ALE-Bench | 785.17 | — |
Reasoning Too close to call
MiMo-V2-Pro: 22.1 (#206), Qwen1.5-14B: 21.4 (#223)
| Benchmark | MiMo-V2-Pro | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | 1457 | 1113 |
| NYT Connections (extended) | 25.8% | — |
| Thematic Generalization | 45.9% | — |
Math MiMo-V2-Pro leads
MiMo-V2-Pro: 39.5 (#102), Qwen1.5-14B: 32.4 (#215)
| Benchmark | MiMo-V2-Pro | Qwen1.5-14B |
|---|---|---|
| LMArena Math | 1447 | 1125 |
Knowledge MiMo-V2-Pro leads
MiMo-V2-Pro: 41.4 (#111), Qwen1.5-14B: 29.8 (#232)
| Benchmark | MiMo-V2-Pro | Qwen1.5-14B |
|---|---|---|
| LMArena Expert | 1478 | 1094 |
| MMLU | — | 68.6% |
Multilingual MiMo-V2-Pro leads
MiMo-V2-Pro: 52.7 (#81), Qwen1.5-14B: 30.7 (#262)
| Benchmark | MiMo-V2-Pro | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | 1416 | 1095 |
| LMArena Chinese | 1456 | 1147 |
| LMArena French | 1469 | 1116 |
| LMArena German | 1417 | 1043 |
| LMArena Japanese | 1366 | 1019 |
| LMArena Russian | 1427 | 1046 |
| LMArena Spanish | 1457 | 1085 |
| LMArena Korean | 1400 | — |
Instruction Following MiMo-V2-Pro leads
MiMo-V2-Pro: 76.0 (#49), Qwen1.5-14B: 56.8 (#271)
| Benchmark | MiMo-V2-Pro | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | 1445 | 1102 |
Long Context MiMo-V2-Pro leads
MiMo-V2-Pro: 41.5 (#138), Qwen1.5-14B: 33.7 (#257)
| Benchmark | MiMo-V2-Pro | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | 1455 | 1113 |
| CL-bench | 15.7% | — |
| CL-bench Life | 6.9% | — |
Writing & Preference MiMo-V2-Pro leads
MiMo-V2-Pro: 62.8 (#70), Qwen1.5-14B: 33.6 (#276)
| Benchmark | MiMo-V2-Pro | Qwen1.5-14B |
|---|---|---|
| LMArena Text | 1436 | 1128 |
| LMArena Creative Writing | 1415 | 1091 |
| LMArena Multi-Turn | 1456 | 1110 |
Frequently asked questions
Is MiMo-V2-Pro better than Qwen1.5-14B?
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 32.7 on the Noometry Index.
Is MiMo-V2-Pro or Qwen1.5-14B better for coding?
MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 33.1 in the Noometry coding category.
How many benchmarks do MiMo-V2-Pro and Qwen1.5-14B share?
16 benchmarks have published results for both models. MiMo-V2-Pro has 23 scored results on Noometry and Qwen1.5-14B has 17.