# Codellama 70b Instruct vs Qwen3.8 27B

> Qwen3.8 27B is the stronger model overall, scoring 46.0 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-qwen3-8-27b
- 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 Qwen3.8 27B in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.8 27B leads 65.8 to 33.4.

## Snapshot

| | Codellama 70b Instruct | Qwen3.8 27B |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 33.7 | 46.0 |
| Rank | 237 | 68 |
| Context | — | 262K |
| Input $/M | — | $0.99 |
| Output $/M | — | $1.49 |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- Qwen3.8 27B: 50.5 (#44)

| Benchmark | Codellama 70b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena WebDev | — | 1593 |
| SciCode | — | 46.6% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1482 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- Qwen3.8 27B: 32.9 (#57)

| Benchmark | Codellama 70b Instruct | Qwen3.8 27B |
|---|---|---|
| APEX-Agents | — | 47.5% |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- Qwen3.8 27B: 41.0 (#54)

| Benchmark | Codellama 70b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1460 |
| ARC-AGI-2 | — | 42.4% |
| NYT Connections (extended) | — | 54.5% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 5.4% |
| DTBench | — | 88% |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
| Epoch Capabilities Index | — | 149.38 |

## Math

- Codellama 70b Instruct: —
- Qwen3.8 27B: 37.1 (#161)

| Benchmark | Codellama 70b Instruct | Qwen3.8 27B |
|---|---|---|
| ProofBench | — | 16% |
| LMArena Math | — | 1456 |

## Knowledge

- Codellama 70b Instruct: —
- Qwen3.8 27B: 41.6 (#109)

| Benchmark | Codellama 70b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | — | 1482 |

## Multimodal

- Codellama 70b Instruct: —
- Qwen3.8 27B: 41.3 (#37)

| Benchmark | Codellama 70b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1271 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- Qwen3.8 27B: 53.7 (#60)

| Benchmark | Codellama 70b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 992 | 1430 |
| LMArena Chinese | — | 1504 |
| LMArena French | — | 1465 |
| LMArena German | — | 1438 |
| LMArena Japanese | — | 1384 |
| LMArena Korean | — | 1393 |
| LMArena Russian | — | 1415 |
| LMArena Spanish | — | 1448 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- Qwen3.8 27B: 75.8 (#53)

| Benchmark | Codellama 70b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1439 |

## Long Context

- Codellama 70b Instruct: —
- Qwen3.8 27B: 44.3 (#70)

| Benchmark | Codellama 70b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | — | 1450 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- Qwen3.8 27B: 65.8 (#43)

| Benchmark | Codellama 70b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1057 | 1441 |
| LMArena Creative Writing | — | 1384 |
| EQ-Bench Creative Writing | — | 1671 |
| LMArena Multi-Turn | — | 1441 |

## FAQ

### Is Codellama 70b Instruct better than Qwen3.8 27B?

Qwen3.8 27B is the stronger model overall, scoring 46.0 to 33.7 on the Noometry Index.

### Is Codellama 70b Instruct or Qwen3.8 27B better for coding?

Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 37.6 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Qwen3.8 27B share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Qwen3.8 27B has 31.