Model comparison
MiniMax-M2 vs Qwen3-4B
MiniMax-M2 is the stronger model overall, scoring 36.9 to 31.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- The widest gap is in math, where MiniMax-M2 leads 34.6 to 28.5.
Side by side
| MiniMax-M2 | Qwen3-4B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 36.9 | 31.5 |
| Released | 2025-10-27 | 2025-04-29 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 21 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
MiniMax-M2: 39.1 (#151), Qwen3-4B: —
| Benchmark | MiniMax-M2 | Qwen3-4B |
|---|---|---|
| SWE-bench Verified (bash only) | 61% | — |
| LMArena WebDev | 1297 | — |
| LMArena Coding | 1370 | — |
Agentic & Tool Use Qwen3-4B leads
MiniMax-M2: 24.9 (#102), Qwen3-4B: 27.3 (#94)
| Benchmark | MiniMax-M2 | Qwen3-4B |
|---|---|---|
| Terminal-Bench | 30% | — |
| Berkeley Function Calling Leaderboard | — | 35.7% |
| Vending-Bench 2 | 160.6 | — |
Reasoning Too close to call
MiniMax-M2: 18.6 (#256), Qwen3-4B: 18.5 (#264)
| Benchmark | MiniMax-M2 | Qwen3-4B |
|---|---|---|
| Kagi LLM Benchmark | 57.8% | — |
| NYT Connections (extended) | 14.8% | — |
| Chess Puzzles | — | 4% |
| LMArena Hard Prompts | 1357 | — |
Math MiniMax-M2 leads
MiniMax-M2: 34.6 (#158), Qwen3-4B: 28.5 (#228)
| Benchmark | MiniMax-M2 | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 38.5% |
| OTIS Mock AIME 2024-2025 | — | 52.2% |
| LMArena Math | 1350 | — |
Knowledge MiniMax-M2 leads
MiniMax-M2: 36.3 (#160), Qwen3-4B: 33.0 (#198)
| Benchmark | MiniMax-M2 | Qwen3-4B |
|---|---|---|
| GPQA Diamond | — | 52.3% |
| Vectara Hallucination Rate | — | 5.7% |
| LMArena Expert | 1336 | — |
Multilingual Not comparable
MiniMax-M2: 45.6 (#165), Qwen3-4B: —
| Benchmark | MiniMax-M2 | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1314 | — |
| LMArena Chinese | 1367 | — |
| LMArena French | 1336 | — |
| LMArena German | 1366 | — |
| LMArena Russian | 1332 | — |
| LMArena Spanish | 1326 | — |
Instruction Following Not comparable
MiniMax-M2: 70.4 (#160), Qwen3-4B: —
| Benchmark | MiniMax-M2 | Qwen3-4B |
|---|---|---|
| LMArena Instruction Following | 1329 | — |
Long Context Not comparable
MiniMax-M2: 40.5 (#148), Qwen3-4B: —
| Benchmark | MiniMax-M2 | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1332 | — |
Writing & Preference Not comparable
MiniMax-M2: 53.3 (#157), Qwen3-4B: —
| Benchmark | MiniMax-M2 | Qwen3-4B |
|---|---|---|
| LMArena Text | 1340 | — |
| LMArena Creative Writing | 1288 | — |
| LMArena Multi-Turn | 1362 | — |
Frequently asked questions
Is MiniMax-M2 better than Qwen3-4B?
MiniMax-M2 is the stronger model overall, scoring 36.9 to 31.5 on the Noometry Index.
How many benchmarks do MiniMax-M2 and Qwen3-4B share?
0 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Qwen3-4B has 6.