# GLM-4.7 vs Llama 3-70B

> GLM-4.7 is the stronger model overall, scoring 41.7 to 28.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-7-vs-llama-3-70b
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. GLM-4.7 scores higher in 9 categories and Llama 3-70B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.7 leads 47.0 to 20.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.3% for GLM-4.7 and 4.3% for Llama 3-70B.

## Snapshot

| | GLM-4.7 | Llama 3-70B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 41.7 | 28.5 |
| Rank | 117 | 317 |
| Context | 205K | — |
| Input $/M | $0.60 | — |
| Output $/M | $2.20 | — |
| Weights | Open | Open |

## Coding

- GLM-4.7: 43.6 (#74)
- Llama 3-70B: 35.3 (#215)

| Benchmark | GLM-4.7 | Llama 3-70B |
|---|---|---|
| LMArena Coding | 1454 | 1206 |
| LMArena WebDev | 1435 | — |
| SciCode | 45.1% | — |
| BigCodeBench Instruct | — | 43.6% |
| BigCodeBench Complete | — | 54.5% |
| ALE-Bench | 399.48 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |

## Agentic & Tool Use

- GLM-4.7: 26.4 (#96)
- Llama 3-70B: 20.9 (#132)

| Benchmark | GLM-4.7 | Llama 3-70B |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Cybench | — | 5% |
| Vending-Bench 2 | 2,377 | — |

## Reasoning

- GLM-4.7: 23.7 (#161)
- Llama 3-70B: 17.4 (#284)

| Benchmark | GLM-4.7 | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1195 |
| Epoch Capabilities Index | 143.53 | 122.91 |
| SimpleBench | 47.7% | — |
| Kagi LLM Benchmark | — | 35.1% |
| CritPt | 1.7% | — |
| Chess Puzzles | 6% | — |
| DTBench | — | 54.2% |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |

## Math

- GLM-4.7: 37.7 (#92)
- Llama 3-70B: 12.0 (#299)

| Benchmark | GLM-4.7 | Llama 3-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 4.3% |
| LMArena Math | 1423 | 1218 |
| ProofBench | 6% | — |
| MATH Level 5 | — | 22.6% |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- GLM-4.7: 47.0 (#74)
- Llama 3-70B: 20.8 (#272)

| Benchmark | GLM-4.7 | Llama 3-70B |
|---|---|---|
| GPQA Diamond | 83.3% | 40.6% |
| LMArena Expert | 1424 | 1149 |
| SimpleQA Verified | 32.2% | — |
| Vectara Hallucination Rate | 11.7% | — |
| MMLU | — | 79.3% |

## Multilingual

- GLM-4.7: 53.0 (#75)
- Llama 3-70B: 33.8 (#246)

| Benchmark | GLM-4.7 | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1417 | 1142 |
| LMArena Chinese | 1495 | 1114 |
| LMArena French | 1432 | 1231 |
| LMArena German | 1426 | 1169 |
| LMArena Japanese | 1439 | 1017 |
| LMArena Korean | 1401 | 1017 |
| LMArena Russian | 1423 | 1159 |
| LMArena Spanish | 1433 | 1241 |

## Instruction Following

- GLM-4.7: 74.6 (#90)
- Llama 3-70B: 62.8 (#233)

| Benchmark | GLM-4.7 | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1411 | 1194 |

## Long Context

- GLM-4.7: 42.8 (#111)
- Llama 3-70B: 35.6 (#235)

| Benchmark | GLM-4.7 | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1432 | 1174 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |

## Writing & Preference

- GLM-4.7: 61.1 (#89)
- Llama 3-70B: 43.0 (#225)

| Benchmark | GLM-4.7 | Llama 3-70B |
|---|---|---|
| LMArena Text | 1436 | 1221 |
| LMArena Creative Writing | 1401 | 1210 |
| LMArena Multi-Turn | 1446 | 1223 |
| EQ-Bench Creative Writing | 1413 | — |

## FAQ

### Is GLM-4.7 better than Llama 3-70B?

GLM-4.7 is the stronger model overall, scoring 41.7 to 28.5 on the Noometry Index.

### Is GLM-4.7 or Llama 3-70B better for coding?

GLM-4.7 scores higher on coding benchmarks: 43.6 versus 35.3 in the Noometry coding category.

### How many benchmarks do GLM-4.7 and Llama 3-70B share?

20 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Llama 3-70B has 31.