# Codellama 70b Instruct vs GLM-5

> GLM-5 is the stronger model overall, scoring 46.1 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-glm-5
- Last updated: 2026-10-11
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and GLM-5 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5 leads 66.0 to 33.4.

## Snapshot

| | Codellama 70b Instruct | GLM-5 |
|---|---|---|
| Provider | Meta | Z.ai (Zhipu) |
| Noometry Index | 33.7 | 46.1 |
| Rank | 237 | 66 |
| Context | — | 205K |
| Input $/M | — | $1 |
| Output $/M | — | $3.20 |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- GLM-5: 49.0 (#52)

| Benchmark | Codellama 70b Instruct | GLM-5 |
|---|---|---|
| SWE-bench Verified | — | 72.1% |
| SWE-bench Verified (bash only) | — | 72.8% |
| LMArena WebDev | — | 1434 |
| SWE-bench Multilingual | — | 69.7% |
| WeirdML | — | 48.2% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1461 |
| BigCodeBench Complete | 49.6% | — |
| ALE-Bench | — | 765.62 |
| HumanEval+ | 65.9% | — |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- GLM-5: 31.1 (#71)

| Benchmark | Codellama 70b Instruct | GLM-5 |
|---|---|---|
| Terminal-Bench | — | 52.4% |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 73.7% |
| τ²-bench Telecom | — | 86.8% |
| Vending-Bench 2 | — | 4,432 |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- GLM-5: 27.6 (#116)

| Benchmark | Codellama 70b Instruct | GLM-5 |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1452 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | — | 53.2% |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 74.8% |
| ARC-AGI-1 | — | 44.7% |
| Chess Puzzles | — | 10% |
| Epoch Capabilities Index | — | 145.83 |
| ForecastBench | — | 61 |

## Math

- Codellama 70b Instruct: —
- GLM-5: 46.4 (#71)

| Benchmark | Codellama 70b Instruct | GLM-5 |
|---|---|---|
| MathArena Final-Answer Competitions | — | 65.7% |
| OTIS Mock AIME 2024-2025 | — | 80% |
| LMArena Math | — | 1440 |
| FrontierMath (Feb 2025 set) | — | 16.4% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Codellama 70b Instruct: —
- GLM-5: 52.3 (#64)

| Benchmark | Codellama 70b Instruct | GLM-5 |
|---|---|---|
| GPQA Diamond | — | 87.8% |
| Vectara Hallucination Rate | — | 10.1% |
| LMArena Expert | — | 1454 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- GLM-5: 53.7 (#58)

| Benchmark | Codellama 70b Instruct | GLM-5 |
|---|---|---|
| LMArena Non-English | 992 | 1430 |
| LMArena Chinese | — | 1511 |
| LMArena French | — | 1455 |
| LMArena German | — | 1445 |
| LMArena Japanese | — | 1416 |
| LMArena Korean | — | 1423 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1454 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- GLM-5: 75.2 (#67)

| Benchmark | Codellama 70b Instruct | GLM-5 |
|---|---|---|
| LMArena Instruction Following | 1024 | 1428 |

## Long Context

- Codellama 70b Instruct: —
- GLM-5: 44.7 (#60)

| Benchmark | Codellama 70b Instruct | GLM-5 |
|---|---|---|
| CL-bench | — | 18.7% |
| LMArena Longer Query | — | 1446 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- GLM-5: 66.0 (#38)

| Benchmark | Codellama 70b Instruct | GLM-5 |
|---|---|---|
| LMArena Text | 1057 | 1446 |
| LMArena Creative Writing | — | 1439 |
| EQ-Bench Creative Writing | — | 1601 |
| LMArena Multi-Turn | — | 1456 |

## FAQ

### Is Codellama 70b Instruct better than GLM-5?

GLM-5 is the stronger model overall, scoring 46.1 to 33.7 on the Noometry Index.

### Is Codellama 70b Instruct or GLM-5 better for coding?

GLM-5 scores higher on coding benchmarks: 49.0 versus 37.6 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and GLM-5 share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and GLM-5 has 45.