# GLM-4.7 vs QwQ-32B

> GLM-4.7 is the stronger model overall, scoring 42.0 to 39.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-7-vs-qwq-32b
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. GLM-4.7 scores higher in 7 categories and QwQ-32B in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.7 leads 60.9 to 50.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.3% for GLM-4.7 and 59.2% for QwQ-32B.

## Snapshot

| | GLM-4.7 | QwQ-32B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 42.0 | 39.8 |
| Rank | 124 | 159 |
| Context | 205K | — |
| Input $/M | $0.60 | — |
| Output $/M | $2.20 | — |
| Weights | Open | Open |

## Coding

- GLM-4.7: 44.0 (#79)
- QwQ-32B: 35.4 (#226)

| Benchmark | GLM-4.7 | QwQ-32B |
|---|---|---|
| LMArena Coding | 1454 | 1333 |
| Aider Polyglot | — | 20.9% |
| LMArena WebDev | 1435 | — |
| SciCode | 45.1% | — |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
| ALE-Bench | 399.48 | — |

## Agentic & Tool Use

- GLM-4.7: 26.5 (#103)
- QwQ-32B: —

| Benchmark | GLM-4.7 | QwQ-32B |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Vending-Bench 2 | 2,377 | — |

## Reasoning

- GLM-4.7: 24.3 (#164)
- QwQ-32B: 23.7 (#174)

| Benchmark | GLM-4.7 | QwQ-32B |
|---|---|---|
| Chess Puzzles | 6% | 5% |
| LMArena Hard Prompts | 1443 | 1325 |
| Epoch Capabilities Index | 143.51 | 137.6 |
| SimpleBench | 47.7% | — |
| CritPt | 1.7% | — |
| LiveBench Reasoning | — | 83.5% |
| LiveBench Data Analysis | — | 65% |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |

## Math

- GLM-4.7: 38.6 (#135)
- QwQ-32B: 38.0 (#143)

| Benchmark | GLM-4.7 | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 59.2% |
| LMArena Math | 1423 | 1359 |
| ProofBench | 6% | — |
| LiveBench Math | — | 77.8% |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- GLM-4.7: 47.0 (#80)
- QwQ-32B: 37.2 (#158)

| Benchmark | GLM-4.7 | QwQ-32B |
|---|---|---|
| GPQA Diamond | 83.3% | 65.3% |
| LMArena Expert | 1424 | 1324 |
| SimpleQA Verified | 32.2% | — |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | 11.7% | — |

## Multilingual

- GLM-4.7: 52.8 (#79)
- QwQ-32B: 44.8 (#176)

| Benchmark | GLM-4.7 | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1417 | 1305 |
| LMArena Chinese | 1495 | 1378 |
| LMArena French | 1432 | 1336 |
| LMArena German | 1424 | 1313 |
| LMArena Japanese | 1439 | 1262 |
| LMArena Korean | 1399 | 1279 |
| LMArena Russian | 1423 | 1297 |
| LMArena Spanish | 1434 | 1354 |

## Instruction Following

- GLM-4.7: 74.4 (#95)
- QwQ-32B: 72.6 (#137)

| Benchmark | GLM-4.7 | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1411 | 1297 |
| LiveBench Instruction Following | — | 81.8% |

## Long Context

- GLM-4.7: 42.8 (#116)
- QwQ-32B: 49.0 (#11)

| Benchmark | GLM-4.7 | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1432 | 1308 |
| Fiction.LiveBench | — | 83.3% |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |

## Writing & Preference

- GLM-4.7: 60.9 (#93)
- QwQ-32B: 50.6 (#180)

| Benchmark | GLM-4.7 | QwQ-32B |
|---|---|---|
| LMArena Text | 1435 | 1329 |
| LMArena Creative Writing | 1401 | 1288 |
| EQ-Bench Creative Writing | 1413 | 1257 |
| LMArena Multi-Turn | 1446 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| LiveBench Language | — | 51.4% |

## FAQ

### Is GLM-4.7 better than QwQ-32B?

GLM-4.7 is the stronger model overall, scoring 42.0 to 39.8 on the Noometry Index.

### Is GLM-4.7 or QwQ-32B better for coding?

GLM-4.7 scores higher on coding benchmarks: 44.0 versus 35.4 in the Noometry coding category.

### How many benchmarks do GLM-4.7 and QwQ-32B share?

22 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and QwQ-32B has 36.