Model comparison
MiMo-V2-Pro vs Qwen3-4B
MiMo-V2-Pro is the stronger model overall, scoring 42.4 to 31.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in math, where MiMo-V2-Pro leads 36.7 to 28.5.
- Qwen3-4B has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2-Pro | Qwen3-4B | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 42.4 | 31.5 |
| Released | 2026-03-18 | 2025-04-29 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.43 | — |
| Output $ / M tokens | $0.87 | — |
| Results tracked | 23 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
MiMo-V2-Pro: 43.4 (#76), Qwen3-4B: —
| Benchmark | MiMo-V2-Pro | Qwen3-4B |
|---|---|---|
| LMArena WebDev | 1433 | — |
| LMArena Coding | 1476 | — |
| ALE-Bench | 785.17 | — |
Agentic & Tool Use Not comparable
MiMo-V2-Pro: —, Qwen3-4B: 27.3 (#94)
| Benchmark | MiMo-V2-Pro | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 35.7% |
Reasoning MiMo-V2-Pro leads
MiMo-V2-Pro: 21.3 (#200), Qwen3-4B: 18.5 (#264)
| Benchmark | MiMo-V2-Pro | Qwen3-4B |
|---|---|---|
| NYT Connections (extended) | 25.8% | — |
| Chess Puzzles | — | 4% |
| Thematic Generalization | 45.9% | — |
| LMArena Hard Prompts | 1457 | — |
Math MiMo-V2-Pro leads
MiMo-V2-Pro: 36.7 (#104), Qwen3-4B: 28.5 (#228)
| Benchmark | MiMo-V2-Pro | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 38.5% |
| OTIS Mock AIME 2024-2025 | — | 52.2% |
| LMArena Math | 1447 | — |
Knowledge MiMo-V2-Pro leads
MiMo-V2-Pro: 40.8 (#106), Qwen3-4B: 33.0 (#198)
| Benchmark | MiMo-V2-Pro | Qwen3-4B |
|---|---|---|
| GPQA Diamond | — | 52.3% |
| Vectara Hallucination Rate | — | 5.7% |
| LMArena Expert | 1479 | — |
Multilingual Not comparable
MiMo-V2-Pro: 52.9 (#77), Qwen3-4B: —
| Benchmark | MiMo-V2-Pro | Qwen3-4B |
|---|---|---|
| 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 Not comparable
MiMo-V2-Pro: 76.2 (#46), Qwen3-4B: —
| Benchmark | MiMo-V2-Pro | Qwen3-4B |
|---|---|---|
| LMArena Instruction Following | 1444 | — |
Long Context Not comparable
MiMo-V2-Pro: 41.5 (#133), Qwen3-4B: —
| Benchmark | MiMo-V2-Pro | Qwen3-4B |
|---|---|---|
| CL-bench | 15.7% | — |
| CL-bench Life | 6.9% | — |
| LMArena Longer Query | 1455 | — |
Writing & Preference Not comparable
MiMo-V2-Pro: 62.9 (#67), Qwen3-4B: —
| Benchmark | MiMo-V2-Pro | Qwen3-4B |
|---|---|---|
| LMArena Text | 1436 | — |
| LMArena Creative Writing | 1415 | — |
| LMArena Multi-Turn | 1456 | — |
Frequently asked questions
Is MiMo-V2-Pro better than Qwen3-4B?
MiMo-V2-Pro is the stronger model overall, scoring 42.4 to 31.5 on the Noometry Index.
How many benchmarks do MiMo-V2-Pro and Qwen3-4B share?
0 benchmarks have published results for both models. MiMo-V2-Pro has 23 scored results on Noometry and Qwen3-4B has 6.