# Codellama 34b Instruct vs GLM-4.7-Flash

> GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 30.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-34b-instruct-vs-glm-4-7-flash
- Last updated: 2026-10-10
- 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-Flash in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GLM-4.7-Flash leads 46.8 to 25.9.

## Snapshot

| | Codellama 34b Instruct | GLM-4.7-Flash |
|---|---|---|
| Provider | Meta | Z.ai (Zhipu) |
| Noometry Index | 30.2 | 38.4 |
| Rank | 285 | 175 |
| Context | — | 200K |
| Input $/M | — | $0.06 |
| Output $/M | — | $0.40 |
| Weights | Open | Open |

## Coding

- Codellama 34b Instruct: 28.0 (#310)
- GLM-4.7-Flash: 40.0 (#133)

| Benchmark | Codellama 34b Instruct | GLM-4.7-Flash |
|---|---|---|
| LMArena Coding | 1046 | 1383 |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |

## Reasoning

- Codellama 34b Instruct: 18.8 (#250)
- GLM-4.7-Flash: 20.2 (#224)

| Benchmark | Codellama 34b Instruct | GLM-4.7-Flash |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1356 |
| Chess Puzzles | — | 0% |

## Math

- Codellama 34b Instruct: 28.5 (#227)
- GLM-4.7-Flash: 34.4 (#159)

| Benchmark | Codellama 34b Instruct | GLM-4.7-Flash |
|---|---|---|
| LMArena Math | 1056 | 1354 |
| OTIS Mock AIME 2024-2025 | — | 58.3% |

## Knowledge

- Codellama 34b Instruct: —
- GLM-4.7-Flash: 35.4 (#177)

| Benchmark | Codellama 34b Instruct | GLM-4.7-Flash |
|---|---|---|
| GPQA Diamond | — | 60.5% |
| Vectara Hallucination Rate | — | 9.3% |
| LMArena Expert | — | 1357 |

## Multilingual

- Codellama 34b Instruct: 25.9 (#279)
- GLM-4.7-Flash: 46.8 (#152)

| Benchmark | Codellama 34b Instruct | GLM-4.7-Flash |
|---|---|---|
| LMArena Non-English | 1011 | 1331 |
| LMArena Chinese | 976 | 1403 |
| LMArena French | — | 1332 |
| LMArena German | — | 1336 |
| LMArena Korean | — | 1284 |
| LMArena Russian | — | 1333 |
| LMArena Spanish | — | 1351 |

## Instruction Following

- Codellama 34b Instruct: 52.4 (#286)
- GLM-4.7-Flash: 70.3 (#162)

| Benchmark | Codellama 34b Instruct | GLM-4.7-Flash |
|---|---|---|
| LMArena Instruction Following | 1028 | 1327 |

## Long Context

- Codellama 34b Instruct: 30.8 (#279)
- GLM-4.7-Flash: 40.9 (#143)

| Benchmark | Codellama 34b Instruct | GLM-4.7-Flash |
|---|---|---|
| LMArena Longer Query | 1014 | 1345 |

## Writing & Preference

- Codellama 34b Instruct: 28.4 (#292)
- GLM-4.7-Flash: 47.7 (#206)

| Benchmark | Codellama 34b Instruct | GLM-4.7-Flash |
|---|---|---|
| LMArena Text | 1066 | 1351 |
| LMArena Creative Writing | 1032 | 1297 |
| LMArena Multi-Turn | 1015 | 1342 |
| EQ-Bench Creative Writing | — | 1125 |

## FAQ

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

GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 30.2 on the Noometry Index.

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

GLM-4.7-Flash scores higher on coding benchmarks: 40.0 versus 28.0 in the Noometry coding category.

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

10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and GLM-4.7-Flash has 21.