# GLM-4.7-Flash vs Llama 2-70B

> GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 24.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-7-flash-vs-llama-2-70b
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. GLM-4.7-Flash scores higher in 8 categories and Llama 2-70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.7-Flash leads 35.4 to 7.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 58.3% for GLM-4.7-Flash and 0% for Llama 2-70B.

## Snapshot

| | GLM-4.7-Flash | Llama 2-70B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 38.4 | 24.1 |
| Rank | 175 | 343 |
| Context | 200K | — |
| Input $/M | $0.06 | — |
| Output $/M | $0.40 | — |
| Weights | Open | Open |

## Coding

- GLM-4.7-Flash: 40.0 (#133)
- Llama 2-70B: 30.8 (#281)

| Benchmark | GLM-4.7-Flash | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1383 | 1079 |

## Reasoning

- GLM-4.7-Flash: 20.2 (#224)
- Llama 2-70B: 13.7 (#324)

| Benchmark | GLM-4.7-Flash | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1356 | 1073 |
| Chess Puzzles | 0% | — |
| 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-4.7-Flash: 34.4 (#159)
- Llama 2-70B: 7.5 (#320)

| Benchmark | GLM-4.7-Flash | Llama 2-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 58.3% | 0% |
| LMArena Math | 1354 | 1091 |
| MATH Level 5 | — | 3.3% |
| GSM8K | — | 69.6% |

## Knowledge

- GLM-4.7-Flash: 35.4 (#177)
- Llama 2-70B: 7.4 (#305)

| Benchmark | GLM-4.7-Flash | Llama 2-70B |
|---|---|---|
| GPQA Diamond | 60.5% | 26.3% |
| LMArena Expert | 1357 | 1039 |
| Vectara Hallucination Rate | 9.3% | — |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |

## Multilingual

- GLM-4.7-Flash: 46.8 (#152)
- Llama 2-70B: 27.9 (#269)

| Benchmark | GLM-4.7-Flash | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1331 | 1045 |
| LMArena Chinese | 1403 | 994 |
| LMArena French | 1332 | 1089 |
| LMArena German | 1336 | 1041 |
| LMArena Korean | 1284 | 964 |
| LMArena Russian | 1333 | 1083 |
| LMArena Spanish | 1351 | 1142 |
| LMArena Japanese | — | 927 |

## Instruction Following

- GLM-4.7-Flash: 70.3 (#162)
- Llama 2-70B: 55.1 (#273)

| Benchmark | GLM-4.7-Flash | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1327 | 1071 |

## Long Context

- GLM-4.7-Flash: 40.9 (#143)
- Llama 2-70B: 32.2 (#265)

| Benchmark | GLM-4.7-Flash | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1345 | 1062 |

## Writing & Preference

- GLM-4.7-Flash: 47.7 (#206)
- Llama 2-70B: 32.5 (#274)

| Benchmark | GLM-4.7-Flash | Llama 2-70B |
|---|---|---|
| LMArena Text | 1351 | 1115 |
| LMArena Creative Writing | 1297 | 1075 |
| LMArena Multi-Turn | 1342 | 1088 |
| EQ-Bench Creative Writing | 1125 | — |

## FAQ

### Is GLM-4.7-Flash better than Llama 2-70B?

GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 24.1 on the Noometry Index.

### Is GLM-4.7-Flash or Llama 2-70B better for coding?

GLM-4.7-Flash scores higher on coding benchmarks: 40.0 versus 30.8 in the Noometry coding category.

### How many benchmarks do GLM-4.7-Flash and Llama 2-70B share?

18 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and Llama 2-70B has 35.