# MiniMax-M2.7 vs QwQ-32B

> QwQ-32B is the stronger model overall, scoring 39.4 to 37.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m2-7-vs-qwq-32b
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. MiniMax-M2.7 scores higher in 4 categories and QwQ-32B in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where QwQ-32B leads 36.2 to 24.9.

## Snapshot

| | MiniMax-M2.7 | QwQ-32B |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 37.4 | 39.4 |
| Rank | 188 | 153 |
| Context | 205K | — |
| Input $/M | $0.30 | — |
| Output $/M | $1.20 | — |
| Weights | Open | Open |

## Coding

- MiniMax-M2.7: 41.4 (#115)
- QwQ-32B: 34.9 (#220)

| Benchmark | MiniMax-M2.7 | QwQ-32B |
|---|---|---|
| LMArena Coding | 1454 | 1333 |
| Aider Polyglot | — | 20.9% |
| LMArena WebDev | 1397 | — |
| SciCode | 47% | — |
| WeirdML | 37% | — |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
| ALE-Bench | 599.25 | — |

## Agentic & Tool Use

- MiniMax-M2.7: 24.9 (#103)
- QwQ-32B: —

| Benchmark | MiniMax-M2.7 | QwQ-32B |
|---|---|---|
| Terminal-Bench | 45.1% | — |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |

## Reasoning

- MiniMax-M2.7: 19.0 (#248)
- QwQ-32B: 22.9 (#171)

| Benchmark | MiniMax-M2.7 | QwQ-32B |
|---|---|---|
| LMArena Hard Prompts | 1422 | 1326 |
| Epoch Capabilities Index | 145.84 | 137.6 |
| NYT Connections (extended) | 24.7% | — |
| CritPt | 0.6% | — |
| Chess Puzzles | — | 5% |
| Thematic Generalization | 39.3% | — |
| LiveBench Reasoning | — | 83.5% |
| LiveBench Data Analysis | — | 65% |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |

## Math

- MiniMax-M2.7: 24.9 (#254)
- QwQ-32B: 36.2 (#123)

| Benchmark | MiniMax-M2.7 | QwQ-32B |
|---|---|---|
| LMArena Math | 1420 | 1359 |
| OTIS Mock AIME 2024-2025 | — | 59.2% |
| ProofBench | 3% | — |
| LiveBench Math | — | 77.8% |

## Knowledge

- MiniMax-M2.7: 37.1 (#151)
- QwQ-32B: 37.2 (#150)

| Benchmark | MiniMax-M2.7 | QwQ-32B |
|---|---|---|
| LMArena Expert | 1443 | 1323 |
| GPQA Diamond | — | 65.3% |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | 12.9% | — |

## Multilingual

- MiniMax-M2.7: 50.5 (#120)
- QwQ-32B: 45.0 (#171)

| Benchmark | MiniMax-M2.7 | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1382 | 1306 |
| LMArena Chinese | 1439 | 1378 |
| LMArena French | 1422 | 1337 |
| LMArena German | 1398 | 1313 |
| LMArena Japanese | 1261 | 1263 |
| LMArena Korean | 1313 | 1278 |
| LMArena Russian | 1383 | 1297 |
| LMArena Spanish | 1403 | 1353 |

## Instruction Following

- MiniMax-M2.7: 74.2 (#101)
- QwQ-32B: 72.8 (#131)

| Benchmark | MiniMax-M2.7 | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1404 | 1297 |
| LiveBench Instruction Following | — | 81.8% |

## Long Context

- MiniMax-M2.7: 43.3 (#94)
- QwQ-32B: 49.0 (#11)

| Benchmark | MiniMax-M2.7 | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1419 | 1308 |
| Fiction.LiveBench | — | 83.3% |

## Writing & Preference

- MiniMax-M2.7: 59.1 (#107)
- QwQ-32B: 50.9 (#175)

| Benchmark | MiniMax-M2.7 | QwQ-32B |
|---|---|---|
| LMArena Text | 1404 | 1329 |
| LMArena Creative Writing | 1354 | 1288 |
| LMArena Multi-Turn | 1413 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |
| LiveBench Language | — | 51.4% |

## FAQ

### Is MiniMax-M2.7 better than QwQ-32B?

QwQ-32B is the stronger model overall, scoring 39.4 to 37.4 on the Noometry Index.

### Is MiniMax-M2.7 or QwQ-32B better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.4 versus 34.9 in the Noometry coding category.

### How many benchmarks do MiniMax-M2.7 and QwQ-32B share?

18 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and QwQ-32B has 36.