Model comparison
Codellama 34b Instruct vs Qwen Max
Qwen Max is the stronger model overall, scoring 34.7 to 30.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 1 category and Qwen Max in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen Max leads 47.8 to 28.2.
- Codellama 34b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 34b Instruct | Qwen Max | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.8 | 34.7 |
| Released | — | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | — | 33K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.60 |
| Output $ / M tokens | — | $6.40 |
| Results tracked | 14 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Max leads
Codellama 34b Instruct: 28.5 (#314), Qwen Max: 30.7 (#292)
| Benchmark | Codellama 34b Instruct | Qwen Max |
|---|---|---|
| LMArena Coding | 1046 | 1288 |
| Aider Polyglot | — | 21.8% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning Qwen Max leads
Codellama 34b Instruct: 19.6 (#255), Qwen Max: 25.1 (#151)
| Benchmark | Codellama 34b Instruct | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1269 |
Math Codellama 34b Instruct leads
Codellama 34b Instruct: 31.0 (#230), Qwen Max: 22.3 (#276)
| Benchmark | Codellama 34b Instruct | Qwen Max |
|---|---|---|
| LMArena Math | 1056 | 1275 |
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Not comparable
Codellama 34b Instruct: —, Qwen Max: 30.3 (#228)
| Benchmark | Codellama 34b Instruct | Qwen Max |
|---|---|---|
| GPQA Diamond | — | 56.1% |
| LMArena Expert | — | 1248 |
Multilingual Qwen Max leads
Codellama 34b Instruct: 25.8 (#284), Qwen Max: 41.8 (#202)
| Benchmark | Codellama 34b Instruct | Qwen Max |
|---|---|---|
| LMArena Non-English | 1011 | 1263 |
| LMArena Chinese | 976 | 1254 |
| LMArena French | — | 1330 |
| LMArena German | — | 1254 |
| LMArena Japanese | — | 1205 |
| LMArena Korean | — | 1142 |
| LMArena Russian | — | 1274 |
| LMArena Spanish | — | 1290 |
Instruction Following Qwen Max leads
Codellama 34b Instruct: 52.2 (#291), Qwen Max: 66.5 (#208)
| Benchmark | Codellama 34b Instruct | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1028 | 1262 |
Long Context Qwen Max leads
Codellama 34b Instruct: 30.9 (#284), Qwen Max: 39.4 (#180)
| Benchmark | Codellama 34b Instruct | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1013 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Qwen Max leads
Codellama 34b Instruct: 28.2 (#297), Qwen Max: 47.8 (#205)
| Benchmark | Codellama 34b Instruct | Qwen Max |
|---|---|---|
| LMArena Text | 1066 | 1282 |
| LMArena Creative Writing | 1032 | 1248 |
| LMArena Multi-Turn | 1015 | 1277 |
Frequently asked questions
Is Codellama 34b Instruct better than Qwen Max?
Qwen Max is the stronger model overall, scoring 34.7 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or Qwen Max better for coding?
Qwen Max scores higher on coding benchmarks: 30.7 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Qwen Max share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Qwen Max has 23.