Model comparison
MiMo-V2.5-Pro vs Qwen3-4B
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 31.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in math, where MiMo-V2.5-Pro leads 40.0 to 29.7.
Side by side
| MiMo-V2.5-Pro | Qwen3-4B | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 45.2 | 31.9 |
| Released | 2026-04-22 | 2025-04-29 |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.43 | — |
| Output $ / M tokens | $0.87 | — |
| Results tracked | 27 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
MiMo-V2.5-Pro: 47.4 (#60), Qwen3-4B: —
| Benchmark | MiMo-V2.5-Pro | Qwen3-4B |
|---|---|---|
| LMArena WebDev | 1479 | — |
| SciCode | 50.2% | — |
| LMArena Coding | 1503 | — |
| ALE-Bench | 899.8 | — |
Agentic & Tool Use Not comparable
MiMo-V2.5-Pro: —, Qwen3-4B: 27.6 (#100)
| Benchmark | MiMo-V2.5-Pro | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 35.7% |
Reasoning MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 26.8 (#130), Qwen3-4B: 19.2 (#268)
| Benchmark | MiMo-V2.5-Pro | Qwen3-4B |
|---|---|---|
| NYT Connections (extended) | 34.4% | — |
| CritPt | 4% | — |
| Chess Puzzles | — | 4% |
| LMArena Hard Prompts | 1488 | — |
| DTBench | 84.5% | — |
| LMCA | 29.5% | — |
Math MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 40.0 (#96), Qwen3-4B: 29.7 (#240)
| Benchmark | MiMo-V2.5-Pro | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 38.5% |
| OTIS Mock AIME 2024-2025 | — | 52.2% |
| ProofBench | 22% | — |
| LMArena Math | 1481 | — |
Knowledge MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 42.2 (#98), Qwen3-4B: 33.0 (#208)
| Benchmark | MiMo-V2.5-Pro | Qwen3-4B |
|---|---|---|
| GPQA Diamond | — | 52.3% |
| Vectara Hallucination Rate | — | 5.7% |
| LMArena Expert | 1503 | — |
Multilingual Not comparable
MiMo-V2.5-Pro: 55.1 (#34), Qwen3-4B: —
| Benchmark | MiMo-V2.5-Pro | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1449 | — |
| LMArena Chinese | 1507 | — |
| LMArena French | 1488 | — |
| LMArena German | 1458 | — |
| LMArena Japanese | 1412 | — |
| LMArena Korean | 1437 | — |
| LMArena Russian | 1450 | — |
| LMArena Spanish | 1471 | — |
Instruction Following Not comparable
MiMo-V2.5-Pro: 77.5 (#21), Qwen3-4B: —
| Benchmark | MiMo-V2.5-Pro | Qwen3-4B |
|---|---|---|
| LMArena Instruction Following | 1477 | — |
Long Context Not comparable
MiMo-V2.5-Pro: 45.4 (#37), Qwen3-4B: —
| Benchmark | MiMo-V2.5-Pro | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1483 | — |
Writing & Preference Not comparable
MiMo-V2.5-Pro: 65.3 (#49), Qwen3-4B: —
| Benchmark | MiMo-V2.5-Pro | Qwen3-4B |
|---|---|---|
| LMArena Text | 1465 | — |
| LMArena Creative Writing | 1440 | — |
| EQ-Bench Creative Writing | 1493 | — |
| EQ-Bench 4 | 1208 | — |
| LMArena Multi-Turn | 1477 | — |
Frequently asked questions
Is MiMo-V2.5-Pro better than Qwen3-4B?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 31.9 on the Noometry Index.
How many benchmarks do MiMo-V2.5-Pro and Qwen3-4B share?
0 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and Qwen3-4B has 6.