# GLM-4.5 vs Qwen2-72B

> GLM-4.5 is the stronger model overall, scoring 41.4 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-5-vs-qwen2-72b
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. GLM-4.5 scores higher in 8 categories and Qwen2-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GLM-4.5 leads 53.0 to 36.0.
- The biggest single-benchmark swing is WeirdML: 40.6% for GLM-4.5 and 11.3% for Qwen2-72B.

## Snapshot

| | GLM-4.5 | Qwen2-72B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 41.4 | 29.5 |
| Rank | 125 | 294 |
| Context | 131K | — |
| Input $/M | $0.60 | — |
| Output $/M | $2.20 | — |
| Weights | Open | Open |

## Coding

- GLM-4.5: 41.1 (#121)
- Qwen2-72B: 28.7 (#303)

| Benchmark | GLM-4.5 | Qwen2-72B |
|---|---|---|
| WeirdML | 40.6% | 11.3% |
| LMArena Coding | 1434 | 1196 |
| SWE-bench Verified (bash only) | 54.2% | — |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 344.82 | — |
| AlgoTune | 1.52 | — |

## Agentic & Tool Use

- GLM-4.5: —
- Qwen2-72B: 16.9 (#138)

| Benchmark | GLM-4.5 | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- GLM-4.5: 27.7 (#99)
- Qwen2-72B: 22.2 (#184)

| Benchmark | GLM-4.5 | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1430 | 1191 |
| Kagi LLM Benchmark | 57.9% | — |
| Epoch Capabilities Index | — | 125.27 |

## Math

- GLM-4.5: 36.3 (#119)
- Qwen2-72B: 27.9 (#232)

| Benchmark | GLM-4.5 | Qwen2-72B |
|---|---|---|
| LMArena Math | 1427 | 1235 |
| MATH Level 5 | — | 39.1% |

## Knowledge

- GLM-4.5: 35.5 (#172)
- Qwen2-72B: 21.2 (#270)

| Benchmark | GLM-4.5 | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1433 | 1171 |
| GPQA Diamond | — | 40.8% |
| Humanity's Last Exam | 8.3% | — |
| Confabulations | 11.3% | — |
| MMLU | — | 82.4% |

## Multilingual

- GLM-4.5: 53.0 (#74)
- Qwen2-72B: 36.0 (#239)

| Benchmark | GLM-4.5 | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1417 | 1176 |
| LMArena Chinese | 1465 | 1240 |
| LMArena French | 1423 | 1169 |
| LMArena German | 1406 | 1151 |
| LMArena Japanese | 1416 | 1111 |
| LMArena Korean | 1382 | 1083 |
| LMArena Russian | 1414 | 1169 |
| LMArena Spanish | 1454 | 1168 |

## Instruction Following

- GLM-4.5: 74.3 (#100)
- Qwen2-72B: 62.0 (#236)

| Benchmark | GLM-4.5 | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1405 | 1181 |

## Long Context

- GLM-4.5: 38.2 (#196)
- Qwen2-72B: 36.1 (#230)

| Benchmark | GLM-4.5 | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1413 | 1193 |
| Fiction.LiveBench | 58.3% | — |

## Writing & Preference

- GLM-4.5: 57.7 (#121)
- Qwen2-72B: 41.0 (#236)

| Benchmark | GLM-4.5 | Qwen2-72B |
|---|---|---|
| LMArena Text | 1430 | 1203 |
| LMArena Creative Writing | 1395 | 1181 |
| LMArena Multi-Turn | 1415 | 1195 |
| Short-Story Creative Writing | 73.4% | — |
| EQ-Bench Creative Writing | 1343 | — |

## FAQ

### Is GLM-4.5 better than Qwen2-72B?

GLM-4.5 is the stronger model overall, scoring 41.4 to 29.5 on the Noometry Index.

### Is GLM-4.5 or Qwen2-72B better for coding?

GLM-4.5 scores higher on coding benchmarks: 41.1 versus 28.7 in the Noometry coding category.

### How many benchmarks do GLM-4.5 and Qwen2-72B share?

18 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Qwen2-72B has 26.