# GLM-4.6 vs Llama 13b

> GLM-4.6 is the stronger model overall, scoring 41.4 to 24.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-6-vs-llama-13b
- Last updated: 2026-10-11
- Shared benchmarks: 8

## Summary

- They share 8 benchmarks with published results for both. GLM-4.6 scores higher in 6 categories and Llama 13b in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.6 leads 61.1 to 13.8.

## Snapshot

| | GLM-4.6 | Llama 13b |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 41.4 | 24.4 |
| Rank | 135 | 348 |
| Context | 205K | — |
| Input $/M | $0.60 | — |
| Output $/M | $2.20 | — |
| Weights | Open | Open |

## Coding

- GLM-4.6: 40.1 (#148)
- Llama 13b: 21.4 (#337)

| Benchmark | GLM-4.6 | Llama 13b |
|---|---|---|
| LMArena Coding | 1449 | 683 |
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1340 | — |
| SciCode | 38.4% | — |
| ALE-Bench | 340.82 | — |

## Agentic & Tool Use

- GLM-4.6: 32.3 (#66)
- Llama 13b: —

| Benchmark | GLM-4.6 | Llama 13b |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |

## Reasoning

- GLM-4.6: 23.7 (#172)
- Llama 13b: 14.0 (#329)

| Benchmark | GLM-4.6 | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1440 | 728 |
| Kagi LLM Benchmark | 47.4% | — |
| CritPt | 1.1% | — |
| BIG-Bench Hard | — | 37.9% |
| Epoch Capabilities Index | — | 100.58 |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |

## Math

- GLM-4.6: 39.1 (#111)
- Llama 13b: 26.7 (#256)

| Benchmark | GLM-4.6 | Llama 13b |
|---|---|---|
| LMArena Math | 1432 | 838 |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
| GSM8K | — | 20.6% |

## Knowledge

- GLM-4.6: 40.2 (#124)
- Llama 13b: —

| Benchmark | GLM-4.6 | Llama 13b |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | — |
| LMArena Expert | 1431 | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |

## Multimodal

- GLM-4.6: —
- Llama 13b: —

| Benchmark | GLM-4.6 | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |

## Multilingual

- GLM-4.6: 53.5 (#66)
- Llama 13b: 16.6 (#297)

| Benchmark | GLM-4.6 | Llama 13b |
|---|---|---|
| LMArena Non-English | 1426 | 819 |
| LMArena Chinese | 1499 | — |
| LMArena French | 1459 | — |
| LMArena German | 1447 | — |
| LMArena Japanese | 1393 | — |
| LMArena Korean | 1400 | — |
| LMArena Russian | 1419 | — |
| LMArena Spanish | 1436 | — |

## Instruction Following

- GLM-4.6: 74.3 (#98)
- Llama 13b: 36.7 (#305)

| Benchmark | GLM-4.6 | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1410 | 781 |

## Long Context

- GLM-4.6: 43.4 (#94)
- Llama 13b: —

| Benchmark | GLM-4.6 | Llama 13b |
|---|---|---|
| LMArena Longer Query | 1422 | — |

## Writing & Preference

- GLM-4.6: 61.1 (#90)
- Llama 13b: 13.8 (#312)

| Benchmark | GLM-4.6 | Llama 13b |
|---|---|---|
| LMArena Text | 1440 | 834 |
| LMArena Creative Writing | 1411 | 794 |
| LMArena Multi-Turn | 1427 | 753 |
| EQ-Bench Creative Writing | 1411 | — |

## FAQ

### Is GLM-4.6 better than Llama 13b?

GLM-4.6 is the stronger model overall, scoring 41.4 to 24.4 on the Noometry Index.

### Is GLM-4.6 or Llama 13b better for coding?

GLM-4.6 scores higher on coding benchmarks: 40.1 versus 21.4 in the Noometry coding category.

### How many benchmarks do GLM-4.6 and Llama 13b share?

8 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Llama 13b has 21.