# GLM-4.7 vs Llama 3.2 90B

> GLM-4.7 is the stronger model overall, scoring 41.7 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-7-vs-llama-3-2-90b
- Last updated: 2026-10-10
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. GLM-4.7 scores higher in 3 categories and Llama 3.2 90B in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.7 leads 37.7 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.3% for GLM-4.7 and 2.6% for Llama 3.2 90B.

## Snapshot

| | GLM-4.7 | Llama 3.2 90B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 41.7 | 27.1 |
| Rank | 117 | 326 |
| Context | 205K | — |
| Input $/M | $0.60 | — |
| Output $/M | $2.20 | — |
| Weights | Open | Open |

## Coding

- GLM-4.7: 43.6 (#74)
- Llama 3.2 90B: —

| Benchmark | GLM-4.7 | Llama 3.2 90B |
|---|---|---|
| LMArena WebDev | 1435 | — |
| SciCode | 45.1% | — |
| LMArena Coding | 1454 | — |
| ALE-Bench | 399.48 | — |

## Agentic & Tool Use

- GLM-4.7: 26.4 (#96)
- Llama 3.2 90B: 29.7 (#73)

| Benchmark | GLM-4.7 | Llama 3.2 90B |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| BALROG | — | 27.3% |
| Vending-Bench 2 | 2,377 | — |

## Reasoning

- GLM-4.7: 23.7 (#161)
- Llama 3.2 90B: 20.9 (#207)

| Benchmark | GLM-4.7 | Llama 3.2 90B |
|---|---|---|
| Epoch Capabilities Index | 143.53 | 125.5 |
| SimpleBench | 47.7% | — |
| CritPt | 1.7% | — |
| Chess Puzzles | 6% | — |
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1443 | — |

## Math

- GLM-4.7: 37.7 (#92)
- Llama 3.2 90B: 10.4 (#302)

| Benchmark | GLM-4.7 | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 2.6% |
| ProofBench | 6% | — |
| LMArena Math | 1423 | — |
| MATH Level 5 | — | 39.4% |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- GLM-4.7: 47.0 (#74)
- Llama 3.2 90B: 21.7 (#269)

| Benchmark | GLM-4.7 | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | 83.3% | 41% |
| SimpleQA Verified | 32.2% | — |
| Vectara Hallucination Rate | 11.7% | — |
| LMArena Expert | 1424 | — |
| MMLU | — | 80.3% |

## Multimodal

- GLM-4.7: —
- Llama 3.2 90B: 24.9 (#119)

| Benchmark | GLM-4.7 | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |

## Multilingual

- GLM-4.7: 53.0 (#75)
- Llama 3.2 90B: —

| Benchmark | GLM-4.7 | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1417 | — |
| LMArena Chinese | 1495 | — |
| LMArena French | 1432 | — |
| LMArena German | 1426 | — |
| LMArena Japanese | 1439 | — |
| LMArena Korean | 1401 | — |
| LMArena Russian | 1423 | — |
| LMArena Spanish | 1433 | — |

## Instruction Following

- GLM-4.7: 74.6 (#90)
- Llama 3.2 90B: —

| Benchmark | GLM-4.7 | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 1411 | — |

## Long Context

- GLM-4.7: 42.8 (#111)
- Llama 3.2 90B: —

| Benchmark | GLM-4.7 | Llama 3.2 90B |
|---|---|---|
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
| LMArena Longer Query | 1432 | — |

## Writing & Preference

- GLM-4.7: 61.1 (#89)
- Llama 3.2 90B: —

| Benchmark | GLM-4.7 | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1436 | — |
| LMArena Creative Writing | 1401 | — |
| EQ-Bench Creative Writing | 1413 | — |
| LMArena Multi-Turn | 1446 | — |

## FAQ

### Is GLM-4.7 better than Llama 3.2 90B?

GLM-4.7 is the stronger model overall, scoring 41.7 to 27.1 on the Noometry Index.

### How many benchmarks do GLM-4.7 and Llama 3.2 90B share?

3 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Llama 3.2 90B has 9.