Model comparison
Codellama 34b Instruct vs Qwen1.5 4b Chat
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 28.8 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 6 categories and Qwen1.5 4b Chat in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Codellama 34b Instruct leads 28.2 to 23.8.
Side by side
| Codellama 34b Instruct | Qwen1.5 4b Chat | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.8 | 28.8 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Codellama 34b Instruct: 28.5 (#314), Qwen1.5 4b Chat: 29.1 (#308)
| Benchmark | Codellama 34b Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Coding | 1046 | 999 |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning Codellama 34b Instruct leads
Codellama 34b Instruct: 19.6 (#255), Qwen1.5 4b Chat: 18.5 (#279)
| Benchmark | Codellama 34b Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Hard Prompts | 1032 | 976 |
Math Too close to call
Codellama 34b Instruct: 31.0 (#230), Qwen1.5 4b Chat: 30.4 (#234)
| Benchmark | Codellama 34b Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Math | 1056 | 1026 |
Knowledge Not comparable
Codellama 34b Instruct: —, Qwen1.5 4b Chat: 26.7 (#255)
| Benchmark | Codellama 34b Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Expert | — | 980 |
Multilingual Codellama 34b Instruct leads
Codellama 34b Instruct: 25.8 (#284), Qwen1.5 4b Chat: 24.1 (#290)
| Benchmark | Codellama 34b Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Non-English | 1011 | 979 |
| LMArena Chinese | 976 | 1024 |
| LMArena German | — | 902 |
| LMArena Russian | — | 952 |
Instruction Following Codellama 34b Instruct leads
Codellama 34b Instruct: 52.2 (#291), Qwen1.5 4b Chat: 49.0 (#300)
| Benchmark | Codellama 34b Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Instruction Following | 1028 | 978 |
Long Context Too close to call
Codellama 34b Instruct: 30.9 (#284), Qwen1.5 4b Chat: 30.1 (#290)
| Benchmark | Codellama 34b Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Longer Query | 1013 | 988 |
Writing & Preference Codellama 34b Instruct leads
Codellama 34b Instruct: 28.2 (#297), Qwen1.5 4b Chat: 23.8 (#309)
| Benchmark | Codellama 34b Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Text | 1066 | 997 |
| LMArena Creative Writing | 1032 | 969 |
| LMArena Multi-Turn | 1015 | 977 |
Frequently asked questions
Is Codellama 34b Instruct better than Qwen1.5 4b Chat?
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 28.8 on the Noometry Index.
Is Codellama 34b Instruct or Qwen1.5 4b Chat better for coding?
They score almost the same on coding (28.5 vs 29.1); test both on your own repository before choosing.
How many benchmarks do Codellama 34b Instruct and Qwen1.5 4b Chat share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Qwen1.5 4b Chat has 13.