# GLM-5.1 vs QwQ-32B

> GLM-5.1 is the stronger model overall, scoring 47.6 to 39.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-qwq-32b
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. GLM-5.1 scores higher in 7 categories and QwQ-32B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.1 leads 55.0 to 37.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 59.2% for QwQ-32B.

## Snapshot

| | GLM-5.1 | QwQ-32B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 47.6 | 39.4 |
| Rank | 51 | 153 |
| Context | 200K | — |
| Input $/M | $1.40 | — |
| Output $/M | $4.40 | — |
| Weights | Open | Open |

## Coding

- GLM-5.1: 48.5 (#52)
- QwQ-32B: 34.9 (#220)

| Benchmark | GLM-5.1 | QwQ-32B |
|---|---|---|
| LMArena Coding | 1486 | 1333 |
| SWE-bench Verified | 74.2% | — |
| Aider Polyglot | — | 20.9% |
| LMArena WebDev | 1509 | — |
| SciCode | 43.8% | — |
| WeirdML | 57.1% | — |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
| ALE-Bench | 887.1 | — |

## Agentic & Tool Use

- GLM-5.1: 24.8 (#106)
- QwQ-32B: —

| Benchmark | GLM-5.1 | QwQ-32B |
|---|---|---|
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 38.2 (#57)
- QwQ-32B: 22.9 (#171)

| Benchmark | GLM-5.1 | QwQ-32B |
|---|---|---|
| Chess Puzzles | 19% | 5% |
| LMArena Hard Prompts | 1472 | 1326 |
| Epoch Capabilities Index | 149.86 | 137.6 |
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Thematic Generalization | 69.8% | — |
| LiveBench Reasoning | — | 83.5% |
| LiveBench Data Analysis | — | 65% |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |

## Math

- GLM-5.1: 49.0 (#48)
- QwQ-32B: 36.2 (#123)

| Benchmark | GLM-5.1 | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 59.2% |
| LMArena Math | 1472 | 1359 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| LiveBench Math | — | 77.8% |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GLM-5.1: 55.0 (#45)
- QwQ-32B: 37.2 (#150)

| Benchmark | GLM-5.1 | QwQ-32B |
|---|---|---|
| GPQA Diamond | 89.9% | 65.3% |
| LMArena Expert | 1477 | 1323 |
| SimpleQA Verified | 34% | — |
| Confabulations | — | 15.6% |

## Multilingual

- GLM-5.1: 55.2 (#34)
- QwQ-32B: 45.0 (#171)

| Benchmark | GLM-5.1 | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1448 | 1306 |
| LMArena Chinese | 1516 | 1378 |
| LMArena French | 1478 | 1337 |
| LMArena German | 1466 | 1313 |
| LMArena Japanese | 1436 | 1263 |
| LMArena Korean | 1423 | 1278 |
| LMArena Russian | 1453 | 1297 |
| LMArena Spanish | 1467 | 1353 |

## Instruction Following

- GLM-5.1: 76.5 (#41)
- QwQ-32B: 72.8 (#131)

| Benchmark | GLM-5.1 | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1451 | 1297 |
| LiveBench Instruction Following | — | 81.8% |

## Long Context

- GLM-5.1: 44.9 (#51)
- QwQ-32B: 49.0 (#11)

| Benchmark | GLM-5.1 | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1467 | 1308 |
| Fiction.LiveBench | — | 83.3% |

## Writing & Preference

- GLM-5.1: 67.2 (#29)
- QwQ-32B: 50.9 (#175)

| Benchmark | GLM-5.1 | QwQ-32B |
|---|---|---|
| LMArena Text | 1462 | 1329 |
| LMArena Creative Writing | 1454 | 1288 |
| EQ-Bench Creative Writing | 1592 | 1257 |
| LMArena Multi-Turn | 1473 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| LiveBench Language | — | 51.4% |

## FAQ

### Is GLM-5.1 better than QwQ-32B?

GLM-5.1 is the stronger model overall, scoring 47.6 to 39.4 on the Noometry Index.

### Is GLM-5.1 or QwQ-32B better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.5 versus 34.9 in the Noometry coding category.

### How many benchmarks do GLM-5.1 and QwQ-32B share?

22 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and QwQ-32B has 36.