Model comparison
MiniMax-M2.1 vs Qwen2.5-Coder-32B
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 33.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. MiniMax-M2.1 scores higher in 7 categories and Qwen2.5-Coder-32B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.1 leads 40.4 to 22.6.
- MiniMax-M2.1 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
- MiniMax-M2.1 accepts more context: 205K tokens versus 33K.
Side by side
| MiniMax-M2.1 | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 38.9 | 33.4 |
| Released | 2025-12-23 | 2024-09-18 |
| Weights | Open | Open |
| Context window | 205K | 33K |
| Max output | 131K | 29K |
| Input $ / M tokens | $0.30 | $0.66 |
| Output $ / M tokens | $1.20 | $1 |
| Results tracked | 22 | 31 |
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), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | MiniMax-M2.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1421 | 1276 |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| LMArena WebDev | 1384 | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| ALE-Bench | 623.83 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Agentic & Tool Use Not comparable
MiniMax-M2.1: 27.9 (#98), Qwen2.5-Coder-32B: —
| Benchmark | MiniMax-M2.1 | Qwen2.5-Coder-32B |
|---|---|---|
| Terminal-Bench | 36.6% | — |
Reasoning Qwen2.5-Coder-32B leads
MiniMax-M2.1: 16.6 (#302), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | MiniMax-M2.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1411 | 1251 |
| NYT Connections (extended) | 11.2% | — |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| Epoch Capabilities Index | — | 119.49 |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#138), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | MiniMax-M2.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1397 | 1251 |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |
Knowledge MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#147), Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | MiniMax-M2.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1431 | 1221 |
| Vectara Hallucination Rate | 11.8% | — |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multilingual MiniMax-M2.1 leads
MiniMax-M2.1: 50.0 (#128), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | MiniMax-M2.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1378 | 1205 |
| LMArena Chinese | 1430 | 1222 |
| LMArena Russian | 1387 | 1228 |
| LMArena French | 1404 | — |
| LMArena German | 1381 | — |
| LMArena Japanese | 1287 | — |
| LMArena Korean | 1298 | — |
| LMArena Spanish | 1397 | — |
Instruction Following MiniMax-M2.1 leads
MiniMax-M2.1: 73.8 (#112), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | MiniMax-M2.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1400 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context MiniMax-M2.1 leads
MiniMax-M2.1: 43.2 (#101), Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | MiniMax-M2.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1416 | 1251 |
Writing & Preference MiniMax-M2.1 leads
MiniMax-M2.1: 58.3 (#120), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | MiniMax-M2.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1392 | 1230 |
| LMArena Creative Writing | 1361 | 1174 |
| LMArena Multi-Turn | 1396 | 1222 |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is MiniMax-M2.1 better than Qwen2.5-Coder-32B?
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 33.4 on the Noometry Index.
Which is cheaper, MiniMax-M2.1 or Qwen2.5-Coder-32B?
MiniMax-M2.1 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.
Is MiniMax-M2.1 or Qwen2.5-Coder-32B better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 22.6 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.1 does, with 205K tokens against 33K.
How many benchmarks do MiniMax-M2.1 and Qwen2.5-Coder-32B share?
12 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Qwen2.5-Coder-32B has 31.