# GLM-4.6V vs Qwen2-72B

> GLM-4.6V is the stronger model overall, scoring 40.9 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-6v-vs-qwen2-72b
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. GLM-4.6V scores higher in 7 categories and Qwen2-72B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.6V leads 37.4 to 21.2.

## Snapshot

| | GLM-4.6V | Qwen2-72B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 40.9 | 29.5 |
| Rank | 133 | 294 |
| Context | 128K | — |
| Input $/M | $0.30 | — |
| Output $/M | $0.90 | — |
| Weights | Open | Open |

## Coding

- GLM-4.6V: 40.2 (#128)
- Qwen2-72B: 28.7 (#303)

| Benchmark | GLM-4.6V | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1390 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- GLM-4.6V: —
- Qwen2-72B: 16.9 (#138)

| Benchmark | GLM-4.6V | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- GLM-4.6V: 26.5 (#117)
- Qwen2-72B: 22.2 (#184)

| Benchmark | GLM-4.6V | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1368 | 1191 |
| Epoch Capabilities Index | — | 125.27 |

## Math

- GLM-4.6V: —
- Qwen2-72B: 27.9 (#232)

| Benchmark | GLM-4.6V | Qwen2-72B |
|---|---|---|
| LMArena Math | — | 1235 |
| MATH Level 5 | — | 39.1% |

## Knowledge

- GLM-4.6V: 37.4 (#148)
- Qwen2-72B: 21.2 (#270)

| Benchmark | GLM-4.6V | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1372 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |

## Multimodal

- GLM-4.6V: 34.2 (#83)
- Qwen2-72B: —

| Benchmark | GLM-4.6V | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1164 | — |

## Multilingual

- GLM-4.6V: 48.8 (#135)
- Qwen2-72B: 36.0 (#239)

| Benchmark | GLM-4.6V | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1359 | 1176 |
| LMArena Chinese | 1426 | 1240 |
| LMArena Russian | 1341 | 1169 |
| LMArena French | — | 1169 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Spanish | — | 1168 |

## Instruction Following

- GLM-4.6V: 71.6 (#145)
- Qwen2-72B: 62.0 (#236)

| Benchmark | GLM-4.6V | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1351 | 1181 |

## Long Context

- GLM-4.6V: 41.3 (#138)
- Qwen2-72B: 36.1 (#230)

| Benchmark | GLM-4.6V | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1358 | 1193 |

## Writing & Preference

- GLM-4.6V: 56.8 (#132)
- Qwen2-72B: 41.0 (#236)

| Benchmark | GLM-4.6V | Qwen2-72B |
|---|---|---|
| LMArena Text | 1377 | 1203 |
| LMArena Creative Writing | 1347 | 1181 |
| LMArena Multi-Turn | 1359 | 1195 |

## FAQ

### Is GLM-4.6V better than Qwen2-72B?

GLM-4.6V is the stronger model overall, scoring 40.9 to 29.5 on the Noometry Index.

### Is GLM-4.6V or Qwen2-72B better for coding?

GLM-4.6V scores higher on coding benchmarks: 40.2 versus 28.7 in the Noometry coding category.

### How many benchmarks do GLM-4.6V and Qwen2-72B share?

11 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and Qwen2-72B has 26.