Model comparison
MiMo-V2.6-Pro vs Qwen3-4B
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 31.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in math, where MiMo-V2.6-Pro leads 54.5 to 29.7.
Side by side
| MiMo-V2.6-Pro | Qwen3-4B | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 50.3 | 31.9 |
| Released | 2026-09-21 | 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 | 19 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
MiMo-V2.6-Pro: 55.5 (#23), Qwen3-4B: —
| Benchmark | MiMo-V2.6-Pro | Qwen3-4B |
|---|---|---|
| LMArena WebDev | 1629 | — |
| SciCode | 60.9% | — |
| LMArena Coding | 1534 | — |
| ALE-Bench | 1,158 | — |
Agentic & Tool Use MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 37.5 (#35), Qwen3-4B: 27.6 (#100)
| Benchmark | MiMo-V2.6-Pro | Qwen3-4B |
|---|---|---|
| APEX-Agents | 59.5% | — |
| Berkeley Function Calling Leaderboard | — | 35.7% |
Reasoning MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 43.1 (#50), Qwen3-4B: 19.2 (#268)
| Benchmark | MiMo-V2.6-Pro | Qwen3-4B |
|---|---|---|
| CritPt | 26.6% | — |
| Chess Puzzles | — | 4% |
| LMArena Hard Prompts | 1512 | — |
Math MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 54.5 (#45), Qwen3-4B: 29.7 (#240)
| Benchmark | MiMo-V2.6-Pro | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 38.5% |
| OTIS Mock AIME 2024-2025 | — | 52.2% |
| ProofBench | 70% | — |
| LMArena Math | 1494 | — |
Knowledge MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 43.5 (#92), Qwen3-4B: 33.0 (#208)
| Benchmark | MiMo-V2.6-Pro | Qwen3-4B |
|---|---|---|
| GPQA Diamond | — | 52.3% |
| Vectara Hallucination Rate | — | 5.7% |
| LMArena Expert | 1543 | — |
Multimodal Not comparable
MiMo-V2.6-Pro: 40.8 (#43), Qwen3-4B: —
| Benchmark | MiMo-V2.6-Pro | Qwen3-4B |
|---|---|---|
| LMArena Vision | 1264 | — |
Multilingual Not comparable
MiMo-V2.6-Pro: 56.9 (#14), Qwen3-4B: —
| Benchmark | MiMo-V2.6-Pro | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1474 | — |
| LMArena Chinese | 1529 | — |
| LMArena Russian | 1480 | — |
Instruction Following Not comparable
MiMo-V2.6-Pro: 78.2 (#12), Qwen3-4B: —
| Benchmark | MiMo-V2.6-Pro | Qwen3-4B |
|---|---|---|
| LMArena Instruction Following | 1493 | — |
Long Context Not comparable
MiMo-V2.6-Pro: 46.0 (#27), Qwen3-4B: —
| Benchmark | MiMo-V2.6-Pro | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1501 | — |
Writing & Preference Not comparable
MiMo-V2.6-Pro: 66.8 (#33), Qwen3-4B: —
| Benchmark | MiMo-V2.6-Pro | Qwen3-4B |
|---|---|---|
| LMArena Text | 1492 | — |
| LMArena Creative Writing | 1468 | — |
| LMArena Multi-Turn | 1464 | — |
Frequently asked questions
Is MiMo-V2.6-Pro better than Qwen3-4B?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 31.9 on the Noometry Index.
How many benchmarks do MiMo-V2.6-Pro and Qwen3-4B share?
0 benchmarks have published results for both models. MiMo-V2.6-Pro has 19 scored results on Noometry and Qwen3-4B has 6.