# Codellama 70b Instruct vs Hunyuan Turbos 20250226

> Hunyuan Turbos 20250226 is the stronger model overall, scoring 41.3 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-hunyuan-turbos
- 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 Hunyuan Turbos 20250226 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Hunyuan Turbos 20250226 leads 48.9 to 24.8.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Codellama 70b Instruct | Hunyuan Turbos 20250226 |
|---|---|---|
| Provider | Meta | Tencent |
| Noometry Index | 33.7 | 41.3 |
| Rank | 237 | 139 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- Hunyuan Turbos 20250226: 40.0 (#152)

| Benchmark | Codellama 70b Instruct | Hunyuan Turbos 20250226 |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1361 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- Hunyuan Turbos 20250226: 27.8 (#113)

| Benchmark | Codellama 70b Instruct | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1374 |

## Math

- Codellama 70b Instruct: —
- Hunyuan Turbos 20250226: 37.5 (#154)

| Benchmark | Codellama 70b Instruct | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Math | — | 1359 |

## Knowledge

- Codellama 70b Instruct: —
- Hunyuan Turbos 20250226: 37.0 (#161)

| Benchmark | Codellama 70b Instruct | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Expert | — | 1339 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- Hunyuan Turbos 20250226: 48.9 (#136)

| Benchmark | Codellama 70b Instruct | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Non-English | 992 | 1363 |
| LMArena Chinese | — | 1417 |
| LMArena French | — | 1391 |
| LMArena German | — | 1355 |
| LMArena Japanese | — | 1342 |
| LMArena Korean | — | 1351 |
| LMArena Russian | — | 1368 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- Hunyuan Turbos 20250226: 71.0 (#158)

| Benchmark | Codellama 70b Instruct | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Instruction Following | 1024 | 1344 |

## Long Context

- Codellama 70b Instruct: —
- Hunyuan Turbos 20250226: 41.6 (#136)

| Benchmark | Codellama 70b Instruct | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Longer Query | — | 1366 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- Hunyuan Turbos 20250226: 57.4 (#128)

| Benchmark | Codellama 70b Instruct | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Text | 1057 | 1377 |
| LMArena Creative Writing | — | 1359 |
| LMArena Multi-Turn | — | 1387 |

## FAQ

### Is Codellama 70b Instruct better than Hunyuan Turbos 20250226?

Hunyuan Turbos 20250226 is the stronger model overall, scoring 41.3 to 33.7 on the Noometry Index.

### Is Codellama 70b Instruct or Hunyuan Turbos 20250226 better for coding?

Hunyuan Turbos 20250226 scores higher on coding benchmarks: 40.0 versus 37.6 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Hunyuan Turbos 20250226 share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Hunyuan Turbos 20250226 has 16.