# GLM-4.6V vs GPT-4

> GLM-4.6V is the stronger model overall, scoring 41.3 to 29.1 on the Noometry Index.

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

## Summary

- They share 11 benchmarks with published results for both. GLM-4.6V scores higher in 7 categories and GPT-4 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.6V leads 56.6 to 34.9.
- GLM-4.6V is cheaper at $0.30 / $0.90 per million input/output tokens, against $30 / $60 for GPT-4.
- GLM-4.6V accepts more context: 128K tokens versus 8K.
- GLM-4.6V has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-4.6V | GPT-4 |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 41.3 | 29.1 |
| Rank | 137 | 316 |
| Context | 128K | 8K |
| Input $/M | $0.30 | $30 |
| Output $/M | $0.90 | $60 |
| Weights | Open | Proprietary |

## Coding

- GLM-4.6V: 40.9 (#128)
- GPT-4: 31.6 (#283)

| Benchmark | GLM-4.6V | GPT-4 |
|---|---|---|
| LMArena Coding | 1390 | 1254 |
| WeirdML | — | 12.4% |
| BigCodeBench Instruct | — | 46% |
| BigCodeBench Complete | — | 57.2% |
| HumanEval+ | — | 79.3% |

## Agentic & Tool Use

- GLM-4.6V: —
- GPT-4: —

| Benchmark | GLM-4.6V | GPT-4 |
|---|---|---|
| METR Time Horizons | — | 36.1% |

## Reasoning

- GLM-4.6V: 27.6 (#115)
- GPT-4: 17.8 (#289)

| Benchmark | GLM-4.6V | GPT-4 |
|---|---|---|
| LMArena Hard Prompts | 1368 | 1241 |
| Chess Puzzles | — | 4% |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 62.7% |
| LMCA | — | 17.1% |
| BIG-Bench Hard | — | 75.1% |
| Epoch Capabilities Index | — | 125.89 |
| ForecastBench | — | 57.8 |
| HellaSwag | — | 95.3% |
| WinoGrande | — | 87.5% |

## Math

- GLM-4.6V: —
- GPT-4: 10.8 (#309)

| Benchmark | GLM-4.6V | GPT-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 1.1% |
| LMArena Math | — | 1269 |
| MATH Level 5 | — | 23% |
| GSM8K | — | 92% |

## Knowledge

- GLM-4.6V: 38.0 (#149)
- GPT-4: 18.4 (#282)

| Benchmark | GLM-4.6V | GPT-4 |
|---|---|---|
| LMArena Expert | 1371 | 1211 |
| GPQA Diamond | — | 35.7% |
| MMLU | — | 86.4% |
| TriviaQA | — | 84.8% |

## Multimodal

- GLM-4.6V: 34.8 (#90)
- GPT-4: —

| Benchmark | GLM-4.6V | GPT-4 |
|---|---|---|
| LMArena Vision | 1164 | — |

## Multilingual

- GLM-4.6V: 48.6 (#141)
- GPT-4: 40.6 (#215)

| Benchmark | GLM-4.6V | GPT-4 |
|---|---|---|
| LMArena Non-English | 1359 | 1246 |
| LMArena Chinese | 1425 | 1242 |
| LMArena Russian | 1340 | 1251 |
| LMArena French | — | 1283 |
| LMArena German | — | 1251 |
| LMArena Japanese | — | 1209 |
| LMArena Korean | — | 1184 |
| LMArena Spanish | — | 1261 |

## Instruction Following

- GLM-4.6V: 71.4 (#151)
- GPT-4: 65.3 (#222)

| Benchmark | GLM-4.6V | GPT-4 |
|---|---|---|
| LMArena Instruction Following | 1352 | 1241 |

## Long Context

- GLM-4.6V: 41.3 (#143)
- GPT-4: 37.7 (#212)

| Benchmark | GLM-4.6V | GPT-4 |
|---|---|---|
| LMArena Longer Query | 1358 | 1244 |

## Writing & Preference

- GLM-4.6V: 56.6 (#137)
- GPT-4: 34.9 (#268)

| Benchmark | GLM-4.6V | GPT-4 |
|---|---|---|
| LMArena Text | 1377 | 1263 |
| LMArena Creative Writing | 1347 | 1244 |
| LMArena Multi-Turn | 1360 | 1257 |
| EQ-Bench Creative Writing | — | 752 |

## FAQ

### Is GLM-4.6V better than GPT-4?

GLM-4.6V is the stronger model overall, scoring 41.3 to 29.1 on the Noometry Index.

### Which is cheaper, GLM-4.6V or GPT-4?

GLM-4.6V is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; GPT-4 lists at $30 and $60.

### Is GLM-4.6V or GPT-4 better for coding?

GLM-4.6V scores higher on coding benchmarks: 40.9 versus 31.6 in the Noometry coding category.

### Which has the bigger context window?

GLM-4.6V does, with 128K tokens against 8K.

### How many benchmarks do GLM-4.6V and GPT-4 share?

11 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and GPT-4 has 38.