Model comparison
MiniMax-M2.1 vs Qwen2-72B
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 30.0 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 8 categories and Qwen2-72B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.1 leads 58.3 to 40.8.
Side by side
| MiniMax-M2.1 | Qwen2-72B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 38.9 | 30.0 |
| Released | 2025-12-23 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 22 | 26 |
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), Qwen2-72B: 29.1 (#310)
| Benchmark | MiniMax-M2.1 | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1421 | 1196 |
| LMArena WebDev | 1384 | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 623.83 | — |
Agentic & Tool Use MiniMax-M2.1 leads
MiniMax-M2.1: 27.9 (#98), Qwen2-72B: 17.0 (#146)
| Benchmark | MiniMax-M2.1 | Qwen2-72B |
|---|---|---|
| Terminal-Bench | 36.6% | — |
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
MiniMax-M2.1: 16.6 (#302), Qwen2-72B: 23.2 (#181)
| Benchmark | MiniMax-M2.1 | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1411 | 1191 |
| NYT Connections (extended) | 11.2% | — |
| Epoch Capabilities Index | — | 125.28 |
Math MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#138), Qwen2-72B: 30.2 (#236)
| Benchmark | MiniMax-M2.1 | Qwen2-72B |
|---|---|---|
| LMArena Math | 1397 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#147), Qwen2-72B: 21.2 (#275)
| Benchmark | MiniMax-M2.1 | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1431 | 1171 |
| GPQA Diamond | — | 40.8% |
| Vectara Hallucination Rate | 11.8% | — |
| MMLU | — | 82.4% |
Multilingual MiniMax-M2.1 leads
MiniMax-M2.1: 50.0 (#128), Qwen2-72B: 35.9 (#244)
| Benchmark | MiniMax-M2.1 | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1378 | 1176 |
| LMArena Chinese | 1430 | 1240 |
| LMArena French | 1404 | 1170 |
| LMArena German | 1381 | 1151 |
| LMArena Japanese | 1287 | 1111 |
| LMArena Korean | 1298 | 1083 |
| LMArena Russian | 1387 | 1169 |
| LMArena Spanish | 1397 | 1169 |
Instruction Following MiniMax-M2.1 leads
MiniMax-M2.1: 73.8 (#112), Qwen2-72B: 61.7 (#241)
| Benchmark | MiniMax-M2.1 | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1400 | 1181 |
Long Context MiniMax-M2.1 leads
MiniMax-M2.1: 43.2 (#101), Qwen2-72B: 36.1 (#235)
| Benchmark | MiniMax-M2.1 | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1416 | 1192 |
Writing & Preference MiniMax-M2.1 leads
MiniMax-M2.1: 58.3 (#120), Qwen2-72B: 40.8 (#241)
| Benchmark | MiniMax-M2.1 | Qwen2-72B |
|---|---|---|
| LMArena Text | 1392 | 1203 |
| LMArena Creative Writing | 1361 | 1181 |
| LMArena Multi-Turn | 1396 | 1196 |
Frequently asked questions
Is MiniMax-M2.1 better than Qwen2-72B?
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 30.0 on the Noometry Index.
Is MiniMax-M2.1 or Qwen2-72B better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 29.1 in the Noometry coding category.
How many benchmarks do MiniMax-M2.1 and Qwen2-72B share?
17 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Qwen2-72B has 26.