# Codellama 34b Instruct vs GLM-4.7

> GLM-4.7 is the stronger model overall, scoring 42.0 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-34b-instruct-vs-glm-4-7
- Last updated: 2026-10-11
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 0 categories and GLM-4.7 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.7 leads 60.9 to 28.2.

## Snapshot

| | Codellama 34b Instruct | GLM-4.7 |
|---|---|---|
| Provider | Meta | Z.ai (Zhipu) |
| Noometry Index | 30.8 | 42.0 |
| Rank | 287 | 124 |
| Context | — | 205K |
| Input $/M | — | $0.60 |
| Output $/M | — | $2.20 |
| Weights | Open | Open |

## Coding

- Codellama 34b Instruct: 28.5 (#314)
- GLM-4.7: 44.0 (#79)

| Benchmark | Codellama 34b Instruct | GLM-4.7 |
|---|---|---|
| LMArena Coding | 1046 | 1454 |
| LMArena WebDev | — | 1435 |
| SciCode | — | 45.1% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| ALE-Bench | — | 399.48 |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |

## Agentic & Tool Use

- Codellama 34b Instruct: —
- GLM-4.7: 26.5 (#103)

| Benchmark | Codellama 34b Instruct | GLM-4.7 |
|---|---|---|
| Terminal-Bench | — | 33.4% |
| Vending-Bench 2 | — | 2,377 |

## Reasoning

- Codellama 34b Instruct: 19.6 (#255)
- GLM-4.7: 24.3 (#164)

| Benchmark | Codellama 34b Instruct | GLM-4.7 |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1443 |
| SimpleBench | — | 47.7% |
| CritPt | — | 1.7% |
| Chess Puzzles | — | 6% |
| Epoch Capabilities Index | — | 143.51 |

## Math

- Codellama 34b Instruct: 31.0 (#230)
- GLM-4.7: 38.6 (#135)

| Benchmark | Codellama 34b Instruct | GLM-4.7 |
|---|---|---|
| LMArena Math | 1056 | 1423 |
| OTIS Mock AIME 2024-2025 | — | 83.3% |
| ProofBench | — | 6% |
| FrontierMath (Feb 2025 set) | — | 2.4% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Codellama 34b Instruct: —
- GLM-4.7: 47.0 (#80)

| Benchmark | Codellama 34b Instruct | GLM-4.7 |
|---|---|---|
| GPQA Diamond | — | 83.3% |
| SimpleQA Verified | — | 32.2% |
| Vectara Hallucination Rate | — | 11.7% |
| LMArena Expert | — | 1424 |

## Multilingual

- Codellama 34b Instruct: 25.8 (#284)
- GLM-4.7: 52.8 (#79)

| Benchmark | Codellama 34b Instruct | GLM-4.7 |
|---|---|---|
| LMArena Non-English | 1011 | 1417 |
| LMArena Chinese | 976 | 1495 |
| LMArena French | — | 1432 |
| LMArena German | — | 1424 |
| LMArena Japanese | — | 1439 |
| LMArena Korean | — | 1399 |
| LMArena Russian | — | 1423 |
| LMArena Spanish | — | 1434 |

## Instruction Following

- Codellama 34b Instruct: 52.2 (#291)
- GLM-4.7: 74.4 (#95)

| Benchmark | Codellama 34b Instruct | GLM-4.7 |
|---|---|---|
| LMArena Instruction Following | 1028 | 1411 |

## Long Context

- Codellama 34b Instruct: 30.9 (#284)
- GLM-4.7: 42.8 (#116)

| Benchmark | Codellama 34b Instruct | GLM-4.7 |
|---|---|---|
| LMArena Longer Query | 1013 | 1432 |
| CL-bench | — | 15.9% |
| CL-bench Life | — | 10.9% |

## Writing & Preference

- Codellama 34b Instruct: 28.2 (#297)
- GLM-4.7: 60.9 (#93)

| Benchmark | Codellama 34b Instruct | GLM-4.7 |
|---|---|---|
| LMArena Text | 1066 | 1435 |
| LMArena Creative Writing | 1032 | 1401 |
| LMArena Multi-Turn | 1015 | 1446 |
| EQ-Bench Creative Writing | — | 1413 |

## FAQ

### Is Codellama 34b Instruct better than GLM-4.7?

GLM-4.7 is the stronger model overall, scoring 42.0 to 30.8 on the Noometry Index.

### Is Codellama 34b Instruct or GLM-4.7 better for coding?

GLM-4.7 scores higher on coding benchmarks: 44.0 versus 28.5 in the Noometry coding category.

### How many benchmarks do Codellama 34b Instruct and GLM-4.7 share?

10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and GLM-4.7 has 36.