Model comparison
MiniMax-M2.1 vs Qwen1.5-32B
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 30.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. MiniMax-M2.1 scores higher in 7 categories and Qwen1.5-32B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2.1 leads 38.3 to 13.5.
Side by side
| MiniMax-M2.1 | Qwen1.5-32B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 38.9 | 30.5 |
| Released | 2025-12-23 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 22 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
MiniMax-M2.1: 40.4 (#143), Qwen1.5-32B: 31.7 (#282)
| Benchmark | MiniMax-M2.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1421 | 1155 |
| LMArena WebDev | 1384 | — |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
| ALE-Bench | 623.83 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.1: 27.9 (#98), Qwen1.5-32B: —
| Benchmark | MiniMax-M2.1 | Qwen1.5-32B |
|---|---|---|
| Terminal-Bench | 36.6% | — |
Reasoning Qwen1.5-32B leads
MiniMax-M2.1: 16.6 (#302), Qwen1.5-32B: 21.8 (#212)
| Benchmark | MiniMax-M2.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1411 | 1130 |
| NYT Connections (extended) | 11.2% | — |
Math MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#138), Qwen1.5-32B: 33.0 (#207)
| Benchmark | MiniMax-M2.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1397 | 1155 |
Knowledge MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#147), Qwen1.5-32B: 13.5 (#296)
| Benchmark | MiniMax-M2.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Expert | 1431 | 1126 |
| GPQA Diamond | — | 30.7% |
| Vectara Hallucination Rate | 11.8% | — |
| MMLU | — | 74.4% |
Multilingual MiniMax-M2.1 leads
MiniMax-M2.1: 50.0 (#128), Qwen1.5-32B: 31.4 (#259)
| Benchmark | MiniMax-M2.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1378 | 1106 |
| LMArena Chinese | 1430 | 1177 |
| LMArena French | 1404 | 1101 |
| LMArena German | 1381 | 1058 |
| LMArena Japanese | 1287 | 1027 |
| LMArena Korean | 1298 | 1008 |
| LMArena Russian | 1387 | 1073 |
| LMArena Spanish | 1397 | 1089 |
Instruction Following MiniMax-M2.1 leads
MiniMax-M2.1: 73.8 (#112), Qwen1.5-32B: 57.7 (#265)
| Benchmark | MiniMax-M2.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1400 | 1116 |
Long Context MiniMax-M2.1 leads
MiniMax-M2.1: 43.2 (#101), Qwen1.5-32B: 34.7 (#246)
| Benchmark | MiniMax-M2.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1416 | 1146 |
Writing & Preference MiniMax-M2.1 leads
MiniMax-M2.1: 58.3 (#120), Qwen1.5-32B: 34.2 (#271)
| Benchmark | MiniMax-M2.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1392 | 1137 |
| LMArena Creative Writing | 1361 | 1083 |
| LMArena Multi-Turn | 1396 | 1140 |
Frequently asked questions
Is MiniMax-M2.1 better than Qwen1.5-32B?
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 30.5 on the Noometry Index.
Is MiniMax-M2.1 or Qwen1.5-32B better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 31.7 in the Noometry coding category.
How many benchmarks do MiniMax-M2.1 and Qwen1.5-32B share?
17 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Qwen1.5-32B has 21.