# GLM-4.5V vs Qwen2-72B

> GLM-4.5V is the stronger model overall, scoring 39.8 to 30.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-5v-vs-qwen2-72b
- Last updated: 2026-10-12
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. GLM-4.5V scores higher in 8 categories and Qwen2-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.5V leads 37.5 to 21.2.

## Snapshot

| | GLM-4.5V | Qwen2-72B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 39.8 | 30.0 |
| Rank | 158 | 300 |
| Context | 64K | — |
| Input $/M | $0.60 | — |
| Output $/M | $1.80 | — |
| Weights | Open | Open |

## Coding

- GLM-4.5V: 39.5 (#155)
- Qwen2-72B: 29.1 (#310)

| Benchmark | GLM-4.5V | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1347 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- GLM-4.5V: —
- Qwen2-72B: 17.0 (#146)

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

## Reasoning

- GLM-4.5V: 27.4 (#119)
- Qwen2-72B: 23.2 (#181)

| Benchmark | GLM-4.5V | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1334 | 1191 |
| Kagi LLM Benchmark | 59.8% | — |
| Epoch Capabilities Index | — | 125.28 |

## Math

- GLM-4.5V: 37.4 (#159)
- Qwen2-72B: 30.2 (#236)

| Benchmark | GLM-4.5V | Qwen2-72B |
|---|---|---|
| LMArena Math | 1354 | 1235 |
| MATH Level 5 | — | 39.1% |

## Knowledge

- GLM-4.5V: 37.5 (#156)
- Qwen2-72B: 21.2 (#275)

| Benchmark | GLM-4.5V | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1353 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |

## Multimodal

- GLM-4.5V: 34.3 (#92)
- Qwen2-72B: —

| Benchmark | GLM-4.5V | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1154 | — |

## Multilingual

- GLM-4.5V: 44.6 (#177)
- Qwen2-72B: 35.9 (#244)

| Benchmark | GLM-4.5V | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1303 | 1176 |
| LMArena Chinese | 1337 | 1240 |
| LMArena Russian | 1298 | 1169 |
| LMArena Spanish | 1336 | 1169 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |

## Instruction Following

- GLM-4.5V: 69.2 (#175)
- Qwen2-72B: 61.7 (#241)

| Benchmark | GLM-4.5V | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1311 | 1181 |

## Long Context

- GLM-4.5V: 39.6 (#171)
- Qwen2-72B: 36.1 (#235)

| Benchmark | GLM-4.5V | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1304 | 1192 |

## Writing & Preference

- GLM-4.5V: 52.5 (#170)
- Qwen2-72B: 40.8 (#241)

| Benchmark | GLM-4.5V | Qwen2-72B |
|---|---|---|
| LMArena Text | 1333 | 1203 |
| LMArena Creative Writing | 1295 | 1181 |
| LMArena Multi-Turn | 1332 | 1196 |

## FAQ

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

GLM-4.5V is the stronger model overall, scoring 39.8 to 30.0 on the Noometry Index.

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

GLM-4.5V scores higher on coding benchmarks: 39.5 versus 29.1 in the Noometry coding category.

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

13 benchmarks have published results for both models. GLM-4.5V has 15 scored results on Noometry and Qwen2-72B has 26.