Model comparison
MiniMax-M2.7 vs Qwen1.5-72B
MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 30.8 on the Noometry Index.
Last verified . 17 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. MiniMax-M2.7 scores higher in 6 categories and Qwen1.5-72B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2.7 leads 37.7 to 11.5.
Side by side
| MiniMax-M2.7 | Qwen1.5-72B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 37.7 | 30.8 |
| Released | 2026-03-18 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 30 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.7 leads
MiniMax-M2.7: 41.8 (#120), Qwen1.5-72B: 31.9 (#277)
| Benchmark | MiniMax-M2.7 | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1454 | 1165 |
| LMArena WebDev | 1398 | — |
| SciCode | 47% | — |
| WeirdML | 37% | — |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| ALE-Bench | 599.25 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Agentic & Tool Use Not comparable
MiniMax-M2.7: 25.1 (#111), Qwen1.5-72B: —
| Benchmark | MiniMax-M2.7 | Qwen1.5-72B |
|---|---|---|
| Terminal-Bench | 45.1% | — |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |
Reasoning Qwen1.5-72B leads
MiniMax-M2.7: 19.7 (#253), Qwen1.5-72B: 22.2 (#203)
| Benchmark | MiniMax-M2.7 | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1422 | 1148 |
| NYT Connections (extended) | 24.7% | — |
| CritPt | 0.6% | — |
| Thematic Generalization | 39.3% | — |
| Epoch Capabilities Index | 145.85 | — |
Math Qwen1.5-72B leads
MiniMax-M2.7: 25.9 (#263), Qwen1.5-72B: 33.2 (#205)
| Benchmark | MiniMax-M2.7 | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1420 | 1164 |
| ProofBench | 3% | — |
Knowledge MiniMax-M2.7 leads
MiniMax-M2.7: 37.7 (#152), Qwen1.5-72B: 11.5 (#300)
| Benchmark | MiniMax-M2.7 | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1444 | 1136 |
| GPQA Diamond | — | 28.8% |
| Vectara Hallucination Rate | 12.9% | — |
Multilingual MiniMax-M2.7 leads
MiniMax-M2.7: 50.3 (#123), Qwen1.5-72B: 33.2 (#253)
| Benchmark | MiniMax-M2.7 | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1382 | 1135 |
| LMArena Chinese | 1441 | 1186 |
| LMArena French | 1421 | 1159 |
| LMArena German | 1398 | 1084 |
| LMArena Japanese | 1262 | 1061 |
| LMArena Korean | 1313 | 1050 |
| LMArena Russian | 1383 | 1104 |
| LMArena Spanish | 1403 | 1110 |
Instruction Following MiniMax-M2.7 leads
MiniMax-M2.7: 74.1 (#103), Qwen1.5-72B: 59.3 (#256)
| Benchmark | MiniMax-M2.7 | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1405 | 1141 |
Long Context MiniMax-M2.7 leads
MiniMax-M2.7: 43.3 (#99), Qwen1.5-72B: 35.1 (#243)
| Benchmark | MiniMax-M2.7 | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1419 | 1157 |
Writing & Preference MiniMax-M2.7 leads
MiniMax-M2.7: 58.9 (#112), Qwen1.5-72B: 37.3 (#258)
| Benchmark | MiniMax-M2.7 | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1405 | 1166 |
| LMArena Creative Writing | 1354 | 1137 |
| LMArena Multi-Turn | 1412 | 1160 |
Frequently asked questions
Is MiniMax-M2.7 better than Qwen1.5-72B?
MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 30.8 on the Noometry Index.
Is MiniMax-M2.7 or Qwen1.5-72B better for coding?
MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 31.9 in the Noometry coding category.
How many benchmarks do MiniMax-M2.7 and Qwen1.5-72B share?
17 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Qwen1.5-72B has 22.