# GLM-5.3 vs Qwen1.5-110B

> GLM-5.3 is the stronger model overall, scoring 54.8 to 34.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-3-vs-qwen1-5-110b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. GLM-5.3 scores higher in 8 categories and Qwen1.5-110B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5.3 leads 75.7 to 38.0.

## Snapshot

| | GLM-5.3 | Qwen1.5-110B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 54.8 | 34.2 |
| Rank | 26 | 234 |
| Context | 1M | — |
| Input $/M | $1.40 | — |
| Output $/M | $4.40 | — |
| Weights | Open | Open |

## Coding

- GLM-5.3: 59.5 (#14)
- Qwen1.5-110B: 33.0 (#264)

| Benchmark | GLM-5.3 | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1496 | 1184 |
| DeepSWE | 69% | — |
| FrontierCode | 40.1% | — |
| CursorBench | 42.6% | — |
| LMArena WebDev | 1622 | — |
| FrontierSWE | 30.2% | — |
| SciCode | 59% | — |
| WeirdML | 75.4% | — |
| BigCodeBench Instruct | — | 35% |
| BigCodeBench Complete | — | 44.4% |
| ALE-Bench | 1,317 | — |

## Agentic & Tool Use

- GLM-5.3: 36.4 (#38)
- Qwen1.5-110B: —

| Benchmark | GLM-5.3 | Qwen1.5-110B |
|---|---|---|
| APEX-Agents | 56.6% | — |
| Vending-Bench 2 | 8,164 | — |

## Reasoning

- GLM-5.3: 46.1 (#46)
- Qwen1.5-110B: 22.7 (#189)

| Benchmark | GLM-5.3 | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1489 | 1168 |
| NYT Connections (extended) | 74.2% | — |
| CritPt | 19.1% | — |
| Chess Puzzles | 21% | — |
| Mystery Game Puzzles | 33% | — |
| DTBench | 87.7% | — |
| LMCA | 55.5% | — |
| Bench to the Future 3 | 0.15 | — |
| Epoch Capabilities Index | 155.61 | — |
| ForecastBench | — | 57.7 |

## Math

- GLM-5.3: 62.3 (#33)
- Qwen1.5-110B: 33.7 (#201)

| Benchmark | GLM-5.3 | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1489 | 1185 |
| FrontierMath (Tiers 1-3) | 68.8% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 91.1% | — |
| ProofBench | 49% | — |

## Knowledge

- GLM-5.3: 58.3 (#37)
- Qwen1.5-110B: 31.2 (#219)

| Benchmark | GLM-5.3 | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1516 | 1144 |
| GPQA Diamond | 90.9% | — |
| SimpleQA Verified | 41% | — |

## Multilingual

- GLM-5.3: 55.7 (#28)
- Qwen1.5-110B: 33.6 (#250)

| Benchmark | GLM-5.3 | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1457 | 1142 |
| LMArena Chinese | 1528 | 1206 |
| LMArena French | 1499 | 1151 |
| LMArena German | 1499 | 1123 |
| LMArena Japanese | 1453 | 1074 |
| LMArena Korean | 1472 | 1044 |
| LMArena Russian | 1463 | 1118 |
| LMArena Spanish | 1460 | 1142 |

## Instruction Following

- GLM-5.3: 77.5 (#23)
- Qwen1.5-110B: 60.3 (#252)

| Benchmark | GLM-5.3 | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1477 | 1158 |

## Long Context

- GLM-5.3: 45.4 (#41)
- Qwen1.5-110B: 35.1 (#242)

| Benchmark | GLM-5.3 | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1482 | 1157 |

## Writing & Preference

- GLM-5.3: 75.7 (#6)
- Qwen1.5-110B: 38.0 (#255)

| Benchmark | GLM-5.3 | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1471 | 1175 |
| LMArena Creative Writing | 1457 | 1148 |
| LMArena Multi-Turn | 1472 | 1160 |
| EQ-Bench Creative Writing | 2075 | — |

## FAQ

### Is GLM-5.3 better than Qwen1.5-110B?

GLM-5.3 is the stronger model overall, scoring 54.8 to 34.2 on the Noometry Index.

### Is GLM-5.3 or Qwen1.5-110B better for coding?

GLM-5.3 scores higher on coding benchmarks: 59.5 versus 33.0 in the Noometry coding category.

### How many benchmarks do GLM-5.3 and Qwen1.5-110B share?

17 benchmarks have published results for both models. GLM-5.3 has 42 scored results on Noometry and Qwen1.5-110B has 20.