# Codellama 70b Instruct vs GLM-4.6

> GLM-4.6 is the stronger model overall, scoring 41.4 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-glm-4-6
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and GLM-4.6 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GLM-4.6 leads 53.5 to 24.8.

## Snapshot

| | Codellama 70b Instruct | GLM-4.6 |
|---|---|---|
| Provider | Meta | Z.ai (Zhipu) |
| Noometry Index | 33.7 | 41.4 |
| Rank | 237 | 135 |
| Context | — | 205K |
| Input $/M | — | $0.60 |
| Output $/M | — | $2.20 |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- GLM-4.6: 40.1 (#148)

| Benchmark | Codellama 70b Instruct | GLM-4.6 |
|---|---|---|
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1340 |
| SciCode | — | 38.4% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1449 |
| BigCodeBench Complete | 49.6% | — |
| ALE-Bench | — | 340.82 |
| HumanEval+ | 65.9% | — |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- GLM-4.6: 32.3 (#66)

| Benchmark | Codellama 70b Instruct | GLM-4.6 |
|---|---|---|
| Terminal-Bench | — | 24.5% |
| Berkeley Function Calling Leaderboard | — | 72.4% |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- GLM-4.6: 23.7 (#172)

| Benchmark | Codellama 70b Instruct | GLM-4.6 |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1440 |
| Kagi LLM Benchmark | — | 47.4% |
| CritPt | — | 1.1% |

## Math

- Codellama 70b Instruct: —
- GLM-4.6: 39.1 (#111)

| Benchmark | Codellama 70b Instruct | GLM-4.6 |
|---|---|---|
| LMArena Math | — | 1432 |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Codellama 70b Instruct: —
- GLM-4.6: 40.2 (#124)

| Benchmark | Codellama 70b Instruct | GLM-4.6 |
|---|---|---|
| Vectara Hallucination Rate | — | 9.5% |
| LMArena Expert | — | 1431 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- GLM-4.6: 53.5 (#66)

| Benchmark | Codellama 70b Instruct | GLM-4.6 |
|---|---|---|
| LMArena Non-English | 992 | 1426 |
| LMArena Chinese | — | 1499 |
| LMArena French | — | 1459 |
| LMArena German | — | 1447 |
| LMArena Japanese | — | 1393 |
| LMArena Korean | — | 1400 |
| LMArena Russian | — | 1419 |
| LMArena Spanish | — | 1436 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- GLM-4.6: 74.3 (#98)

| Benchmark | Codellama 70b Instruct | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | 1024 | 1410 |

## Long Context

- Codellama 70b Instruct: —
- GLM-4.6: 43.4 (#94)

| Benchmark | Codellama 70b Instruct | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | — | 1422 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- GLM-4.6: 61.1 (#90)

| Benchmark | Codellama 70b Instruct | GLM-4.6 |
|---|---|---|
| LMArena Text | 1057 | 1440 |
| LMArena Creative Writing | — | 1411 |
| EQ-Bench Creative Writing | — | 1411 |
| LMArena Multi-Turn | — | 1427 |

## FAQ

### Is Codellama 70b Instruct better than GLM-4.6?

GLM-4.6 is the stronger model overall, scoring 41.4 to 33.7 on the Noometry Index.

### Is Codellama 70b Instruct or GLM-4.6 better for coding?

GLM-4.6 scores higher on coding benchmarks: 40.1 versus 37.6 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and GLM-4.6 share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and GLM-4.6 has 29.