# Codellama 70b Instruct vs Qwen3.5 397B-A17B

> Qwen3.5 397B-A17B 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-qwen3-5-397b-a17b
- Last updated: 2026-10-12
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and Qwen3.5 397B-A17B in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen3.5 397B-A17B leads 53.7 to 24.8.

## Snapshot

| | Codellama 70b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 33.7 | 46.0 |
| Rank | 237 | 67 |
| Context | — | 262K |
| Input $/M | — | $0.60 |
| Output $/M | — | $3.60 |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- Qwen3.5 397B-A17B: 42.0 (#114)

| Benchmark | Codellama 70b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena WebDev | — | 1400 |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1465 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- Qwen3.5 397B-A17B: 33.3 (#53)

| Benchmark | Codellama 70b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- Qwen3.5 397B-A17B: 34.5 (#70)

| Benchmark | Codellama 70b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1448 |
| Kagi LLM Benchmark | — | 73.7% |
| NYT Connections (extended) | — | 58.9% |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 65.1% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 87.5% |
| LMCA | — | 37.9% |
| Epoch Capabilities Index | — | 146.65 |

## Math

- Codellama 70b Instruct: —
- Qwen3.5 397B-A17B: 46.1 (#73)

| Benchmark | Codellama 70b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 31.2% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| LMArena Math | — | 1454 |

## Knowledge

- Codellama 70b Instruct: —
- Qwen3.5 397B-A17B: 53.3 (#58)

| Benchmark | Codellama 70b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| GPQA Diamond | — | 86.4% |
| LMArena Expert | — | 1462 |

## Multimodal

- Codellama 70b Instruct: —
- Qwen3.5 397B-A17B: 40.7 (#44)

| Benchmark | Codellama 70b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1263 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- Qwen3.5 397B-A17B: 53.7 (#59)

| Benchmark | Codellama 70b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 992 | 1430 |
| LMArena Chinese | — | 1500 |
| LMArena French | — | 1461 |
| LMArena German | — | 1447 |
| LMArena Japanese | — | 1426 |
| LMArena Korean | — | 1384 |
| LMArena Russian | — | 1429 |
| LMArena Spanish | — | 1441 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- Qwen3.5 397B-A17B: 75.0 (#77)

| Benchmark | Codellama 70b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1424 |

## Long Context

- Codellama 70b Instruct: —
- Qwen3.5 397B-A17B: 44.1 (#74)

| Benchmark | Codellama 70b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | — | 1442 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- Qwen3.5 397B-A17B: 62.3 (#79)

| Benchmark | Codellama 70b Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1057 | 1438 |
| LMArena Creative Writing | — | 1401 |
| EQ-Bench Creative Writing | — | 1478 |
| LMArena Multi-Turn | — | 1446 |

## FAQ

### Is Codellama 70b Instruct better than Qwen3.5 397B-A17B?

Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 33.7 on the Noometry Index.

### Is Codellama 70b Instruct or Qwen3.5 397B-A17B better for coding?

Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 37.6 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Qwen3.5 397B-A17B share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Qwen3.5 397B-A17B has 36.