# Codellama 70b Instruct vs Qwen3.7 Plus

> Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-qwen3-7-plus
- Last updated: 2026-10-12
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 1 category and Qwen3.7 Plus in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.7 Plus leads 64.3 to 33.4.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Codellama 70b Instruct | Qwen3.7 Plus |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 33.7 | 45.3 |
| Rank | 237 | 72 |
| Context | — | 1M |
| Input $/M | — | $0.40 |
| Output $/M | — | $1.60 |
| Weights | Open | Proprietary |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- Qwen3.7 Plus: 36.6 (#206)

| Benchmark | Codellama 70b Instruct | Qwen3.7 Plus |
|---|---|---|
| FrontierCode | — | 10.2% |
| SciCode | — | 45.5% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1473 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- Qwen3.7 Plus: 21.4 (#138)

| Benchmark | Codellama 70b Instruct | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- Qwen3.7 Plus: 39.3 (#59)

| Benchmark | Codellama 70b Instruct | Qwen3.7 Plus |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1460 |
| NYT Connections (extended) | — | 74.8% |
| CritPt | — | 9.1% |
| Chess Puzzles | — | 24% |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 147.37 |

## Math

- Codellama 70b Instruct: —
- Qwen3.7 Plus: 50.5 (#56)

| Benchmark | Codellama 70b Instruct | Qwen3.7 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 34.4% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| LMArena Math | — | 1466 |

## Knowledge

- Codellama 70b Instruct: —
- Qwen3.7 Plus: 54.9 (#51)

| Benchmark | Codellama 70b Instruct | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | — | 87.9% |
| LMArena Expert | — | 1467 |

## Multimodal

- Codellama 70b Instruct: —
- Qwen3.7 Plus: 41.8 (#33)

| Benchmark | Codellama 70b Instruct | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1279 |
| LMArena Document | — | 1444 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- Qwen3.7 Plus: 54.8 (#38)

| Benchmark | Codellama 70b Instruct | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 992 | 1445 |
| LMArena Chinese | — | 1510 |
| LMArena French | — | 1473 |
| LMArena German | — | 1471 |
| LMArena Japanese | — | 1413 |
| LMArena Korean | — | 1415 |
| LMArena Russian | — | 1457 |
| LMArena Spanish | — | 1457 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- Qwen3.7 Plus: 75.8 (#52)

| Benchmark | Codellama 70b Instruct | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1024 | 1440 |

## Long Context

- Codellama 70b Instruct: —
- Qwen3.7 Plus: 44.5 (#65)

| Benchmark | Codellama 70b Instruct | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | — | 1455 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- Qwen3.7 Plus: 64.3 (#56)

| Benchmark | Codellama 70b Instruct | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1057 | 1455 |
| LMArena Creative Writing | — | 1439 |
| LMArena Multi-Turn | — | 1460 |

## FAQ

### Is Codellama 70b Instruct better than Qwen3.7 Plus?

Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 33.7 on the Noometry Index.

### Is Codellama 70b Instruct or Qwen3.7 Plus better for coding?

They score almost the same on coding (37.6 vs 36.6); test both on your own repository before choosing.

### How many benchmarks do Codellama 70b Instruct and Qwen3.7 Plus share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Qwen3.7 Plus has 32.