# GLM-4.6V vs Llama 2-70B

> GLM-4.6V is the stronger model overall, scoring 40.9 to 24.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-6v-vs-llama-2-70b
- 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 Llama 2-70B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.6V leads 37.4 to 7.4.

## Snapshot

| | GLM-4.6V | Llama 2-70B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 40.9 | 24.1 |
| Rank | 133 | 343 |
| Context | 128K | — |
| Input $/M | $0.30 | — |
| Output $/M | $0.90 | — |
| Weights | Open | Open |

## Coding

- GLM-4.6V: 40.2 (#128)
- Llama 2-70B: 30.8 (#281)

| Benchmark | GLM-4.6V | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1390 | 1079 |

## Reasoning

- GLM-4.6V: 26.5 (#117)
- Llama 2-70B: 13.7 (#324)

| Benchmark | GLM-4.6V | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1368 | 1073 |
| DTBench | — | 41.6% |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| Epoch Capabilities Index | — | 113.59 |
| ForecastBench | — | 51.4 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |

## Math

- GLM-4.6V: —
- Llama 2-70B: 7.5 (#320)

| Benchmark | GLM-4.6V | Llama 2-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 0% |
| LMArena Math | — | 1091 |
| MATH Level 5 | — | 3.3% |
| GSM8K | — | 69.6% |

## Knowledge

- GLM-4.6V: 37.4 (#148)
- Llama 2-70B: 7.4 (#305)

| Benchmark | GLM-4.6V | Llama 2-70B |
|---|---|---|
| LMArena Expert | 1372 | 1039 |
| GPQA Diamond | — | 26.3% |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |

## Multimodal

- GLM-4.6V: 34.2 (#83)
- Llama 2-70B: —

| Benchmark | GLM-4.6V | Llama 2-70B |
|---|---|---|
| LMArena Vision | 1164 | — |

## Multilingual

- GLM-4.6V: 48.8 (#135)
- Llama 2-70B: 27.9 (#269)

| Benchmark | GLM-4.6V | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1359 | 1045 |
| LMArena Chinese | 1426 | 994 |
| LMArena Russian | 1341 | 1083 |
| LMArena French | — | 1089 |
| LMArena German | — | 1041 |
| LMArena Japanese | — | 927 |
| LMArena Korean | — | 964 |
| LMArena Spanish | — | 1142 |

## Instruction Following

- GLM-4.6V: 71.6 (#145)
- Llama 2-70B: 55.1 (#273)

| Benchmark | GLM-4.6V | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1351 | 1071 |

## Long Context

- GLM-4.6V: 41.3 (#138)
- Llama 2-70B: 32.2 (#265)

| Benchmark | GLM-4.6V | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1358 | 1062 |

## Writing & Preference

- GLM-4.6V: 56.8 (#132)
- Llama 2-70B: 32.5 (#274)

| Benchmark | GLM-4.6V | Llama 2-70B |
|---|---|---|
| LMArena Text | 1377 | 1115 |
| LMArena Creative Writing | 1347 | 1075 |
| LMArena Multi-Turn | 1359 | 1088 |

## FAQ

### Is GLM-4.6V better than Llama 2-70B?

GLM-4.6V is the stronger model overall, scoring 40.9 to 24.1 on the Noometry Index.

### Is GLM-4.6V or Llama 2-70B better for coding?

GLM-4.6V scores higher on coding benchmarks: 40.2 versus 30.8 in the Noometry coding category.

### How many benchmarks do GLM-4.6V and Llama 2-70B share?

11 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and Llama 2-70B has 35.