Model comparison
Codellama 34b Instruct vs Qwen-14B
Codellama 34b Instruct and Qwen-14B score almost the same on the Noometry Index (30.8 vs 31.4), so choose on price, context window or the category you care about most.
Last verified . 10 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 2 categories and Qwen-14B in 5 categories; 2 gaps are clear of the uncertainty.
Side by side
| Codellama 34b Instruct | Qwen-14B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.8 | 31.4 |
| Released | — | 2023-09-24 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen-14B leads
Codellama 34b Instruct: 28.5 (#314), Qwen-14B: 31.2 (#288)
| Benchmark | Codellama 34b Instruct | Qwen-14B |
|---|---|---|
| LMArena Coding | 1046 | 1071 |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning Too close to call
Codellama 34b Instruct: 19.6 (#255), Qwen-14B: 19.6 (#257)
| Benchmark | Codellama 34b Instruct | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1027 |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 113.03 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Too close to call
Codellama 34b Instruct: 31.0 (#230), Qwen-14B: 31.2 (#227)
| Benchmark | Codellama 34b Instruct | Qwen-14B |
|---|---|---|
| LMArena Math | 1056 | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Codellama 34b Instruct: —, Qwen-14B: —
| Benchmark | Codellama 34b Instruct | Qwen-14B |
|---|---|---|
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual Qwen-14B leads
Codellama 34b Instruct: 25.8 (#284), Qwen-14B: 27.5 (#275)
| Benchmark | Codellama 34b Instruct | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1011 | 1041 |
| LMArena Chinese | 976 | 1077 |
Instruction Following Too close to call
Codellama 34b Instruct: 52.2 (#291), Qwen-14B: 52.4 (#289)
| Benchmark | Codellama 34b Instruct | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1028 | 1031 |
Long Context Too close to call
Codellama 34b Instruct: 30.9 (#284), Qwen-14B: 31.3 (#280)
| Benchmark | Codellama 34b Instruct | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1013 | 1028 |
Writing & Preference Too close to call
Codellama 34b Instruct: 28.2 (#297), Qwen-14B: 27.6 (#299)
| Benchmark | Codellama 34b Instruct | Qwen-14B |
|---|---|---|
| LMArena Text | 1066 | 1051 |
| LMArena Creative Writing | 1032 | 1028 |
| LMArena Multi-Turn | 1015 | 1022 |
Frequently asked questions
Is Codellama 34b Instruct better than Qwen-14B?
Codellama 34b Instruct and Qwen-14B score almost the same on the Noometry Index (30.8 vs 31.4), so choose on price, context window or the category you care about most.
Is Codellama 34b Instruct or Qwen-14B better for coding?
Qwen-14B scores higher on coding benchmarks: 31.2 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Qwen-14B share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Qwen-14B has 18.