# MiniMax-M2 vs Qwen1.5-72B

> MiniMax-M2 is the stronger model overall, scoring 36.9 to 30.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m2-vs-qwen1-5-72b
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. MiniMax-M2 scores higher in 7 categories and Qwen1.5-72B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2 leads 36.3 to 11.5.

## Snapshot

| | MiniMax-M2 | Qwen1.5-72B |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 36.9 | 30.3 |
| Rank | 201 | 282 |
| Context | 205K | — |
| Input $/M | $0.30 | — |
| Output $/M | $1.20 | — |
| Weights | Open | Open |

## Coding

- MiniMax-M2: 39.1 (#151)
- Qwen1.5-72B: 31.4 (#272)

| Benchmark | MiniMax-M2 | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1370 | 1166 |
| SWE-bench Verified (bash only) | 61% | — |
| LMArena WebDev | 1297 | — |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |

## Agentic & Tool Use

- MiniMax-M2: 24.9 (#102)
- Qwen1.5-72B: —

| Benchmark | MiniMax-M2 | Qwen1.5-72B |
|---|---|---|
| Terminal-Bench | 30% | — |
| Vending-Bench 2 | 160.6 | — |

## Reasoning

- MiniMax-M2: 18.6 (#256)
- Qwen1.5-72B: 21.2 (#201)

| Benchmark | MiniMax-M2 | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1357 | 1148 |
| Kagi LLM Benchmark | 57.8% | — |
| NYT Connections (extended) | 14.8% | — |

## Math

- MiniMax-M2: 34.6 (#158)
- Qwen1.5-72B: 30.7 (#205)

| Benchmark | MiniMax-M2 | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1350 | 1164 |

## Knowledge

- MiniMax-M2: 36.3 (#160)
- Qwen1.5-72B: 11.5 (#295)

| Benchmark | MiniMax-M2 | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1336 | 1136 |
| GPQA Diamond | — | 28.8% |

## Multilingual

- MiniMax-M2: 45.6 (#165)
- Qwen1.5-72B: 33.4 (#248)

| Benchmark | MiniMax-M2 | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1314 | 1135 |
| LMArena Chinese | 1367 | 1186 |
| LMArena French | 1336 | 1158 |
| LMArena German | 1366 | 1084 |
| LMArena Russian | 1332 | 1104 |
| LMArena Spanish | 1326 | 1110 |
| LMArena Japanese | — | 1061 |
| LMArena Korean | — | 1049 |

## Instruction Following

- MiniMax-M2: 70.4 (#160)
- Qwen1.5-72B: 59.6 (#251)

| Benchmark | MiniMax-M2 | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1329 | 1142 |

## Long Context

- MiniMax-M2: 40.5 (#148)
- Qwen1.5-72B: 35.0 (#238)

| Benchmark | MiniMax-M2 | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1332 | 1157 |

## Writing & Preference

- MiniMax-M2: 53.3 (#157)
- Qwen1.5-72B: 37.4 (#253)

| Benchmark | MiniMax-M2 | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1340 | 1166 |
| LMArena Creative Writing | 1288 | 1137 |
| LMArena Multi-Turn | 1362 | 1160 |

## FAQ

### Is MiniMax-M2 better than Qwen1.5-72B?

MiniMax-M2 is the stronger model overall, scoring 36.9 to 30.3 on the Noometry Index.

### Is MiniMax-M2 or Qwen1.5-72B better for coding?

MiniMax-M2 scores higher on coding benchmarks: 39.1 versus 31.4 in the Noometry coding category.

### How many benchmarks do MiniMax-M2 and Qwen1.5-72B share?

15 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Qwen1.5-72B has 22.