Model comparison
MiniMax-M2.1 vs Qwen3-4B
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 31.9 on the Noometry Index.
Last verified . 1 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. MiniMax-M2.1 scores higher in 3 categories and Qwen3-4B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where MiniMax-M2.1 leads 38.3 to 29.7.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 11.8% for MiniMax-M2.1 and 5.7% for Qwen3-4B.
Side by side
| MiniMax-M2.1 | Qwen3-4B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 38.9 | 31.9 |
| Released | 2025-12-23 | 2025-04-29 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 22 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
MiniMax-M2.1: 40.4 (#143), Qwen3-4B: —
| Benchmark | MiniMax-M2.1 | Qwen3-4B |
|---|---|---|
| LMArena WebDev | 1384 | — |
| LMArena Coding | 1421 | — |
| ALE-Bench | 623.83 | — |
Agentic & Tool Use Too close to call
MiniMax-M2.1: 27.9 (#98), Qwen3-4B: 27.6 (#100)
| Benchmark | MiniMax-M2.1 | Qwen3-4B |
|---|---|---|
| Terminal-Bench | 36.6% | — |
| Berkeley Function Calling Leaderboard | — | 35.7% |
Reasoning Qwen3-4B leads
MiniMax-M2.1: 16.6 (#302), Qwen3-4B: 19.2 (#268)
| Benchmark | MiniMax-M2.1 | Qwen3-4B |
|---|---|---|
| NYT Connections (extended) | 11.2% | — |
| Chess Puzzles | — | 4% |
| LMArena Hard Prompts | 1411 | — |
Math MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#138), Qwen3-4B: 29.7 (#240)
| Benchmark | MiniMax-M2.1 | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 38.5% |
| OTIS Mock AIME 2024-2025 | — | 52.2% |
| LMArena Math | 1397 | — |
Knowledge MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#147), Qwen3-4B: 33.0 (#208)
| Benchmark | MiniMax-M2.1 | Qwen3-4B |
|---|---|---|
| Vectara Hallucination Rate | 11.8% | 5.7% |
| GPQA Diamond | — | 52.3% |
| LMArena Expert | 1431 | — |
Multilingual Not comparable
MiniMax-M2.1: 50.0 (#128), Qwen3-4B: —
| Benchmark | MiniMax-M2.1 | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1378 | — |
| LMArena Chinese | 1430 | — |
| LMArena French | 1404 | — |
| LMArena German | 1381 | — |
| LMArena Japanese | 1287 | — |
| LMArena Korean | 1298 | — |
| LMArena Russian | 1387 | — |
| LMArena Spanish | 1397 | — |
Instruction Following Not comparable
MiniMax-M2.1: 73.8 (#112), Qwen3-4B: —
| Benchmark | MiniMax-M2.1 | Qwen3-4B |
|---|---|---|
| LMArena Instruction Following | 1400 | — |
Long Context Not comparable
MiniMax-M2.1: 43.2 (#101), Qwen3-4B: —
| Benchmark | MiniMax-M2.1 | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1416 | — |
Writing & Preference Not comparable
MiniMax-M2.1: 58.3 (#120), Qwen3-4B: —
| Benchmark | MiniMax-M2.1 | Qwen3-4B |
|---|---|---|
| LMArena Text | 1392 | — |
| LMArena Creative Writing | 1361 | — |
| LMArena Multi-Turn | 1396 | — |
Frequently asked questions
Is MiniMax-M2.1 better than Qwen3-4B?
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 31.9 on the Noometry Index.
How many benchmarks do MiniMax-M2.1 and Qwen3-4B share?
1 benchmark has published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Qwen3-4B has 6.