# Codellama 70b Instruct vs Qwen2.5-Max

> Qwen2.5-Max is the stronger model overall, scoring 40.7 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-qwen2-5-max
- 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 Qwen2.5-Max in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen2.5-Max leads 48.1 to 24.8.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Codellama 70b Instruct | Qwen2.5-Max |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 33.7 | 40.7 |
| Rank | 237 | 146 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- Qwen2.5-Max: 41.8 (#117)

| Benchmark | Codellama 70b Instruct | Qwen2.5-Max |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LiveBench Coding | — | 64.4% |
| LMArena Coding | — | 1359 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- Qwen2.5-Max: 25.6 (#147)

| Benchmark | Codellama 70b Instruct | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1360 |
| LiveBench Reasoning | — | 51.4% |
| LiveBench Data Analysis | — | 67.9% |
| Epoch Capabilities Index | — | 132.53 |
| LiveBench | — | 62.3% |

## Math

- Codellama 70b Instruct: —
- Qwen2.5-Max: 36.9 (#162)

| Benchmark | Codellama 70b Instruct | Qwen2.5-Max |
|---|---|---|
| LiveBench Math | — | 58.4% |
| LMArena Math | — | 1369 |

## Knowledge

- Codellama 70b Instruct: —
- Qwen2.5-Max: 35.3 (#186)

| Benchmark | Codellama 70b Instruct | Qwen2.5-Max |
|---|---|---|
| Confabulations | — | 21.8% |
| LMArena Expert | — | 1337 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- Qwen2.5-Max: 48.1 (#146)

| Benchmark | Codellama 70b Instruct | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 992 | 1352 |
| LMArena Chinese | — | 1382 |
| LMArena French | — | 1396 |
| LMArena German | — | 1350 |
| LMArena Japanese | — | 1300 |
| LMArena Korean | — | 1304 |
| LMArena Russian | — | 1353 |
| LMArena Spanish | — | 1377 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- Qwen2.5-Max: 71.3 (#152)

| Benchmark | Codellama 70b Instruct | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1024 | 1335 |
| LiveBench Instruction Following | — | 75.3% |

## Long Context

- Codellama 70b Instruct: —
- Qwen2.5-Max: 41.4 (#142)

| Benchmark | Codellama 70b Instruct | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | — | 1358 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- Qwen2.5-Max: 55.4 (#146)

| Benchmark | Codellama 70b Instruct | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1057 | 1367 |
| LMArena Creative Writing | — | 1339 |
| Short-Story Creative Writing | — | 72.9% |
| LMArena Multi-Turn | — | 1364 |
| LiveBench Language | — | 56.3% |

## FAQ

### Is Codellama 70b Instruct better than Qwen2.5-Max?

Qwen2.5-Max is the stronger model overall, scoring 40.7 to 33.7 on the Noometry Index.

### Is Codellama 70b Instruct or Qwen2.5-Max better for coding?

Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 37.6 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Qwen2.5-Max share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Qwen2.5-Max has 27.