Model comparison
Codellama 34b Instruct vs Llama 13b
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 24.4 on the Noometry Index.
Last verified . 8 shared benchmarks.
MetaSummary
- They share 8 benchmarks with published results for both. Codellama 34b Instruct scores higher in 6 categories and Llama 13b in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Codellama 34b Instruct leads 52.2 to 36.7.
Side by side
| Codellama 34b Instruct | Llama 13b | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 30.8 | 24.4 |
| Released | — | 2023-02-24 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 34b Instruct leads
Codellama 34b Instruct: 28.5 (#314), Llama 13b: 21.4 (#337)
| Benchmark | Codellama 34b Instruct | Llama 13b |
|---|---|---|
| LMArena Coding | 1046 | 683 |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning Codellama 34b Instruct leads
Codellama 34b Instruct: 19.6 (#255), Llama 13b: 14.0 (#329)
| Benchmark | Codellama 34b Instruct | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1032 | 728 |
| BIG-Bench Hard | — | 37.9% |
| Epoch Capabilities Index | — | 100.58 |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |
Math Codellama 34b Instruct leads
Codellama 34b Instruct: 31.0 (#230), Llama 13b: 26.7 (#256)
| Benchmark | Codellama 34b Instruct | Llama 13b |
|---|---|---|
| LMArena Math | 1056 | 838 |
| GSM8K | — | 20.6% |
Knowledge Not comparable
Codellama 34b Instruct: —, Llama 13b: —
| Benchmark | Codellama 34b Instruct | Llama 13b |
|---|---|---|
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
Codellama 34b Instruct: —, Llama 13b: —
| Benchmark | Codellama 34b Instruct | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |
Multilingual Codellama 34b Instruct leads
Codellama 34b Instruct: 25.8 (#284), Llama 13b: 16.6 (#297)
| Benchmark | Codellama 34b Instruct | Llama 13b |
|---|---|---|
| LMArena Non-English | 1011 | 819 |
| LMArena Chinese | 976 | — |
Instruction Following Codellama 34b Instruct leads
Codellama 34b Instruct: 52.2 (#291), Llama 13b: 36.7 (#305)
| Benchmark | Codellama 34b Instruct | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1028 | 781 |
Long Context Not comparable
Codellama 34b Instruct: 30.9 (#284), Llama 13b: —
| Benchmark | Codellama 34b Instruct | Llama 13b |
|---|---|---|
| LMArena Longer Query | 1013 | — |
Writing & Preference Codellama 34b Instruct leads
Codellama 34b Instruct: 28.2 (#297), Llama 13b: 13.8 (#312)
| Benchmark | Codellama 34b Instruct | Llama 13b |
|---|---|---|
| LMArena Text | 1066 | 834 |
| LMArena Creative Writing | 1032 | 794 |
| LMArena Multi-Turn | 1015 | 753 |
Frequently asked questions
Is Codellama 34b Instruct better than Llama 13b?
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 24.4 on the Noometry Index.
Is Codellama 34b Instruct or Llama 13b better for coding?
Codellama 34b Instruct scores higher on coding benchmarks: 28.5 versus 21.4 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Llama 13b share?
8 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Llama 13b has 21.