Model comparison
MiniMax-M2 vs Qwen1.5-32B
MiniMax-M2 is the stronger model overall, scoring 36.9 to 30.0 on the Noometry Index.
Last verified . 15 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 15 benchmarks with published results for both. MiniMax-M2 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 leads 36.3 to 13.5.
Side by side
| MiniMax-M2 | Qwen1.5-32B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 36.9 | 30.0 |
| Released | 2025-10-27 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 21 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
MiniMax-M2: 39.1 (#151), Qwen1.5-32B: 31.1 (#278)
| Benchmark | MiniMax-M2 | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1370 | 1155 |
| SWE-bench Verified (bash only) | 61% | — |
| LMArena WebDev | 1297 | — |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
Agentic & Tool Use Not comparable
MiniMax-M2: 24.9 (#102), Qwen1.5-32B: —
| Benchmark | MiniMax-M2 | Qwen1.5-32B |
|---|---|---|
| Terminal-Bench | 30% | — |
| Vending-Bench 2 | 160.6 | — |
Reasoning Qwen1.5-32B leads
MiniMax-M2: 18.6 (#256), Qwen1.5-32B: 20.9 (#210)
| Benchmark | MiniMax-M2 | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1357 | 1131 |
| Kagi LLM Benchmark | 57.8% | — |
| NYT Connections (extended) | 14.8% | — |
Math MiniMax-M2 leads
MiniMax-M2: 34.6 (#158), Qwen1.5-32B: 30.5 (#207)
| Benchmark | MiniMax-M2 | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1350 | 1155 |
Knowledge MiniMax-M2 leads
MiniMax-M2: 36.3 (#160), Qwen1.5-32B: 13.5 (#291)
| Benchmark | MiniMax-M2 | Qwen1.5-32B |
|---|---|---|
| LMArena Expert | 1336 | 1126 |
| GPQA Diamond | — | 30.7% |
| MMLU | — | 74.4% |
Multilingual MiniMax-M2 leads
MiniMax-M2: 45.6 (#165), Qwen1.5-32B: 31.6 (#254)
| Benchmark | MiniMax-M2 | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1314 | 1106 |
| LMArena Chinese | 1367 | 1176 |
| LMArena French | 1336 | 1100 |
| LMArena German | 1366 | 1058 |
| LMArena Russian | 1332 | 1073 |
| LMArena Spanish | 1326 | 1089 |
| LMArena Japanese | — | 1027 |
| LMArena Korean | — | 1007 |
Instruction Following MiniMax-M2 leads
MiniMax-M2: 70.4 (#160), Qwen1.5-32B: 58.0 (#260)
| Benchmark | MiniMax-M2 | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1329 | 1116 |
Long Context MiniMax-M2 leads
MiniMax-M2: 40.5 (#148), Qwen1.5-32B: 34.7 (#241)
| Benchmark | MiniMax-M2 | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1332 | 1146 |
Writing & Preference MiniMax-M2 leads
MiniMax-M2: 53.3 (#157), Qwen1.5-32B: 34.4 (#266)
| Benchmark | MiniMax-M2 | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1340 | 1137 |
| LMArena Creative Writing | 1288 | 1083 |
| LMArena Multi-Turn | 1362 | 1140 |
Frequently asked questions
Is MiniMax-M2 better than Qwen1.5-32B?
MiniMax-M2 is the stronger model overall, scoring 36.9 to 30.0 on the Noometry Index.
Is MiniMax-M2 or Qwen1.5-32B better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.1 versus 31.1 in the Noometry coding category.
How many benchmarks do MiniMax-M2 and Qwen1.5-32B share?
15 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Qwen1.5-32B has 21.