Model comparison
MiMo-V2-Pro vs Qwen3.8 27B
Qwen3.8 27B is the stronger model overall, scoring 45.3 to 42.4 on the Noometry Index. MiMo-V2-Pro costs 2.1× less per token, which makes it the better buy when Qwen3.8 27B's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. MiMo-V2-Pro scores higher in 2 categories and Qwen3.8 27B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.8 27B leads 31.5 to 21.3.
- The biggest single-benchmark swing is NYT Connections (extended): 25.8% for MiMo-V2-Pro and 54.5% for Qwen3.8 27B.
- MiMo-V2-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $0.99 / $1.49 for Qwen3.8 27B.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 262K.
- Qwen3.8 27B has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2-Pro | Qwen3.8 27B | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 42.4 | 45.3 |
| Released | 2026-03-18 | 2026-08-14 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 131K | 33K |
| Input $ / M tokens | $0.43 | $0.99 |
| Output $ / M tokens | $0.87 | $1.49 |
| Results tracked | 23 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 27B leads
MiMo-V2-Pro: 43.4 (#76), Qwen3.8 27B: 50.3 (#42)
| Benchmark | MiMo-V2-Pro | Qwen3.8 27B |
|---|---|---|
| LMArena WebDev | 1433 | 1592 |
| LMArena Coding | 1476 | 1487 |
| SciCode | — | 46.6% |
| ALE-Bench | 785.17 | — |
Reasoning Qwen3.8 27B leads
MiMo-V2-Pro: 21.3 (#200), Qwen3.8 27B: 31.5 (#71)
| Benchmark | MiMo-V2-Pro | Qwen3.8 27B |
|---|---|---|
| NYT Connections (extended) | 25.8% | 54.5% |
| LMArena Hard Prompts | 1457 | 1459 |
| CritPt | — | 5.4% |
| Thematic Generalization | 45.9% | — |
| DTBench | — | 88% |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
| Epoch Capabilities Index | — | 149.38 |
Math MiMo-V2-Pro leads
MiMo-V2-Pro: 36.7 (#104), Qwen3.8 27B: 35.7 (#139)
| Benchmark | MiMo-V2-Pro | Qwen3.8 27B |
|---|---|---|
| LMArena Math | 1447 | 1453 |
| ProofBench | — | 16% |
Knowledge Too close to call
MiMo-V2-Pro: 40.8 (#106), Qwen3.8 27B: 40.9 (#105)
| Benchmark | MiMo-V2-Pro | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | 1479 | 1482 |
Multimodal Not comparable
MiMo-V2-Pro: —, Qwen3.8 27B: 40.5 (#36)
| Benchmark | MiMo-V2-Pro | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1270 |
Multilingual Qwen3.8 27B leads
MiMo-V2-Pro: 52.9 (#77), Qwen3.8 27B: 54.0 (#54)
| Benchmark | MiMo-V2-Pro | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1416 | 1431 |
| LMArena Chinese | 1455 | 1504 |
| LMArena French | 1470 | 1468 |
| LMArena German | 1417 | 1435 |
| LMArena Japanese | 1366 | 1392 |
| LMArena Korean | 1401 | 1389 |
| LMArena Russian | 1427 | 1421 |
| LMArena Spanish | 1458 | 1444 |
Instruction Following Too close to call
MiMo-V2-Pro: 76.2 (#46), Qwen3.8 27B: 75.8 (#54)
| Benchmark | MiMo-V2-Pro | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1444 | 1436 |
Long Context Qwen3.8 27B leads
MiMo-V2-Pro: 41.5 (#133), Qwen3.8 27B: 44.3 (#66)
| Benchmark | MiMo-V2-Pro | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 1455 | 1448 |
| CL-bench | 15.7% | — |
| CL-bench Life | 6.9% | — |
Writing & Preference Qwen3.8 27B leads
MiMo-V2-Pro: 62.9 (#67), Qwen3.8 27B: 65.9 (#41)
| Benchmark | MiMo-V2-Pro | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1436 | 1441 |
| LMArena Creative Writing | 1415 | 1382 |
| LMArena Multi-Turn | 1456 | 1443 |
| EQ-Bench Creative Writing | — | 1671 |
Frequently asked questions
Is MiMo-V2-Pro better than Qwen3.8 27B?
Qwen3.8 27B is the stronger model overall, scoring 45.3 to 42.4 on the Noometry Index. MiMo-V2-Pro costs 2.1× less per token, which makes it the better buy when Qwen3.8 27B's lead doesn't matter for your workload.
Which is cheaper, MiMo-V2-Pro or Qwen3.8 27B?
MiMo-V2-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Qwen3.8 27B lists at $0.99 and $1.49.
Is MiMo-V2-Pro or Qwen3.8 27B better for coding?
Qwen3.8 27B scores higher on coding benchmarks: 50.3 versus 43.4 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2-Pro does, with 1.05M tokens against 262K.
How many benchmarks do MiMo-V2-Pro and Qwen3.8 27B share?
19 benchmarks have published results for both models. MiMo-V2-Pro has 23 scored results on Noometry and Qwen3.8 27B has 28.