Model comparison
MiMo-V2.5 vs Qwen-14B
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 31.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. MiMo-V2.5 scores higher in 7 categories and Qwen-14B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5 leads 61.6 to 27.6.
Side by side
| MiMo-V2.5 | Qwen-14B | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 43.4 | 31.4 |
| Released | 2026-04-22 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.14 | — |
| Output $ / M tokens | $0.28 | — |
| Results tracked | 23 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
MiMo-V2.5: 43.9 (#81), Qwen-14B: 31.2 (#288)
| Benchmark | MiMo-V2.5 | Qwen-14B |
|---|---|---|
| LMArena Coding | 1469 | 1071 |
| LMArena WebDev | 1438 | — |
| SciCode | 43.1% | — |
| ALE-Bench | 513.95 | — |
Reasoning MiMo-V2.5 leads
MiMo-V2.5: 28.6 (#101), Qwen-14B: 19.6 (#257)
| Benchmark | MiMo-V2.5 | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1450 | 1027 |
| CritPt | 3.7% | — |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 113.03 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math MiMo-V2.5 leads
MiMo-V2.5: 36.8 (#163), Qwen-14B: 31.2 (#227)
| Benchmark | MiMo-V2.5 | Qwen-14B |
|---|---|---|
| LMArena Math | 1436 | 1068 |
| ProofBench | 16% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
MiMo-V2.5: 40.8 (#115), Qwen-14B: —
| Benchmark | MiMo-V2.5 | Qwen-14B |
|---|---|---|
| LMArena Expert | 1460 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multimodal Not comparable
MiMo-V2.5: 39.8 (#54), Qwen-14B: —
| Benchmark | MiMo-V2.5 | Qwen-14B |
|---|---|---|
| LMArena Vision | 1247 | — |
Multilingual MiMo-V2.5 leads
MiMo-V2.5: 51.9 (#99), Qwen-14B: 27.5 (#275)
| Benchmark | MiMo-V2.5 | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1404 | 1041 |
| LMArena Chinese | 1468 | 1077 |
| LMArena French | 1447 | — |
| LMArena German | 1421 | — |
| LMArena Japanese | 1306 | — |
| LMArena Korean | 1363 | — |
| LMArena Russian | 1395 | — |
| LMArena Spanish | 1416 | — |
Instruction Following MiMo-V2.5 leads
MiMo-V2.5: 75.5 (#60), Qwen-14B: 52.4 (#289)
| Benchmark | MiMo-V2.5 | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1434 | 1031 |
Long Context MiMo-V2.5 leads
MiMo-V2.5: 44.2 (#73), Qwen-14B: 31.3 (#280)
| Benchmark | MiMo-V2.5 | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1445 | 1028 |
Writing & Preference MiMo-V2.5 leads
MiMo-V2.5: 61.6 (#86), Qwen-14B: 27.6 (#299)
| Benchmark | MiMo-V2.5 | Qwen-14B |
|---|---|---|
| LMArena Text | 1428 | 1051 |
| LMArena Creative Writing | 1393 | 1028 |
| LMArena Multi-Turn | 1445 | 1022 |
Frequently asked questions
Is MiMo-V2.5 better than Qwen-14B?
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 31.4 on the Noometry Index.
Is MiMo-V2.5 or Qwen-14B better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 31.2 in the Noometry coding category.
How many benchmarks do MiMo-V2.5 and Qwen-14B share?
10 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Qwen-14B has 18.