# DeepSeek-V2.5 (Sep 2024) vs GLM-4.6V

> GLM-4.6V is the stronger model overall, scoring 41.3 to 37.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-glm-4-6v
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and GLM-4.6V in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where GLM-4.6V leads 40.9 to 31.7.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | GLM-4.6V |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 37.6 | 41.3 |
| Rank | 200 | 137 |
| Context | — | 128K |
| Input $/M | — | $0.30 |
| Output $/M | — | $0.90 |
| Weights | Open | Open |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.7 (#281)
- GLM-4.6V: 40.9 (#128)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.6V |
|---|---|---|
| LMArena Coding | 1309 | 1390 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 25.6 (#145)
- GLM-4.6V: 27.6 (#115)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.6V |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1368 |

## Math

- DeepSeek-V2.5 (Sep 2024): 35.9 (#177)
- GLM-4.6V: —

| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.6V |
|---|---|---|
| LMArena Math | 1288 | — |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.8 (#193)
- GLM-4.6V: 38.0 (#149)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.6V |
|---|---|---|
| LMArena Expert | 1266 | 1371 |

## Multimodal

- DeepSeek-V2.5 (Sep 2024): —
- GLM-4.6V: 34.8 (#90)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.6V |
|---|---|---|
| LMArena Vision | — | 1164 |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.5 (#193)
- GLM-4.6V: 48.6 (#141)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.6V |
|---|---|---|
| LMArena Non-English | 1273 | 1359 |
| LMArena Chinese | 1318 | 1425 |
| LMArena Russian | 1289 | 1340 |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.5 (#194)
- GLM-4.6V: 71.4 (#151)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.6V |
|---|---|---|
| LMArena Instruction Following | 1280 | 1352 |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#174)
- GLM-4.6V: 41.3 (#143)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.6V |
|---|---|---|
| LMArena Longer Query | 1301 | 1358 |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 49.8 (#187)
- GLM-4.6V: 56.6 (#137)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.6V |
|---|---|---|
| LMArena Text | 1294 | 1377 |
| LMArena Creative Writing | 1285 | 1347 |
| LMArena Multi-Turn | 1297 | 1360 |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than GLM-4.6V?

GLM-4.6V is the stronger model overall, scoring 41.3 to 37.6 on the Noometry Index.

### Is DeepSeek-V2.5 (Sep 2024) or GLM-4.6V better for coding?

GLM-4.6V scores higher on coding benchmarks: 40.9 versus 31.7 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and GLM-4.6V share?

11 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and GLM-4.6V has 12.