Model comparison
MiniMax M1 vs Qwen2-72B
MiniMax M1 is the stronger model overall, scoring 40.3 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 M1 scores higher in 8 categories and Qwen2-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax M1 leads 36.4 to 21.2.
Side by side
| MiniMax M1 | Qwen2-72B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 40.3 | 30.0 |
| Released | 2025-06-13 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 40K | — |
| Input $ / M tokens | $0.55 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 18 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax M1 leads
MiniMax M1: 39.9 (#153), Qwen2-72B: 29.1 (#310)
| Benchmark | MiniMax M1 | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1359 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
MiniMax M1: —, Qwen2-72B: 17.0 (#146)
| Benchmark | MiniMax M1 | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning MiniMax M1 leads
MiniMax M1: 26.9 (#126), Qwen2-72B: 23.2 (#181)
| Benchmark | MiniMax M1 | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1339 | 1191 |
| Epoch Capabilities Index | — | 125.28 |
Math MiniMax M1 leads
MiniMax M1: 37.5 (#151), Qwen2-72B: 30.2 (#236)
| Benchmark | MiniMax M1 | Qwen2-72B |
|---|---|---|
| LMArena Math | 1361 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge MiniMax M1 leads
MiniMax M1: 36.4 (#170), Qwen2-72B: 21.2 (#275)
| Benchmark | MiniMax M1 | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1317 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |
Multilingual MiniMax M1 leads
MiniMax M1: 45.8 (#163), Qwen2-72B: 35.9 (#244)
| Benchmark | MiniMax M1 | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1319 | 1176 |
| LMArena Chinese | 1360 | 1240 |
| LMArena French | 1370 | 1170 |
| LMArena German | 1350 | 1151 |
| LMArena Japanese | 1217 | 1111 |
| LMArena Korean | 1266 | 1083 |
| LMArena Russian | 1329 | 1169 |
| LMArena Spanish | 1353 | 1169 |
Instruction Following MiniMax M1 leads
MiniMax M1: 69.3 (#174), Qwen2-72B: 61.7 (#241)
| Benchmark | MiniMax M1 | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1312 | 1181 |
Long Context MiniMax M1 leads
MiniMax M1: 41.4 (#141), Qwen2-72B: 36.1 (#235)
| Benchmark | MiniMax M1 | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1326 | 1192 |
| Fiction.LiveBench | 69.4% | — |
Writing & Preference MiniMax M1 leads
MiniMax M1: 53.1 (#161), Qwen2-72B: 40.8 (#241)
| Benchmark | MiniMax M1 | Qwen2-72B |
|---|---|---|
| LMArena Text | 1343 | 1203 |
| LMArena Creative Writing | 1298 | 1181 |
| LMArena Multi-Turn | 1335 | 1196 |
Frequently asked questions
Is MiniMax M1 better than Qwen2-72B?
MiniMax M1 is the stronger model overall, scoring 40.3 to 30.0 on the Noometry Index.
Is MiniMax M1 or Qwen2-72B better for coding?
MiniMax M1 scores higher on coding benchmarks: 39.9 versus 29.1 in the Noometry coding category.
How many benchmarks do MiniMax M1 and Qwen2-72B share?
17 benchmarks have published results for both models. MiniMax M1 has 18 scored results on Noometry and Qwen2-72B has 26.