Model comparison
Codellama 70b Instruct vs Llama 13b
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 24.4 on the Noometry Index.
Last verified . 4 shared benchmarks.
MetaSummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 5 categories and Llama 13b in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Codellama 70b Instruct leads 33.4 to 13.8.
Side by side
| Codellama 70b Instruct | Llama 13b | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 33.7 | 24.4 |
| Released | — | 2023-02-24 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 70b Instruct: 37.6 (#193), Llama 13b: 21.4 (#337)
| Benchmark | Codellama 70b Instruct | Llama 13b |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 683 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning Codellama 70b Instruct leads
Codellama 70b Instruct: 20.1 (#242), Llama 13b: 14.0 (#329)
| Benchmark | Codellama 70b Instruct | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1052 | 728 |
| BIG-Bench Hard | — | 37.9% |
| Epoch Capabilities Index | — | 100.58 |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |
Math Not comparable
Codellama 70b Instruct: —, Llama 13b: 26.7 (#256)
| Benchmark | Codellama 70b Instruct | Llama 13b |
|---|---|---|
| LMArena Math | — | 838 |
| GSM8K | — | 20.6% |
Knowledge Not comparable
Codellama 70b Instruct: —, Llama 13b: —
| Benchmark | Codellama 70b Instruct | Llama 13b |
|---|---|---|
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
Codellama 70b Instruct: —, Llama 13b: —
| Benchmark | Codellama 70b Instruct | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |
Multilingual Codellama 70b Instruct leads
Codellama 70b Instruct: 24.8 (#288), Llama 13b: 16.6 (#297)
| Benchmark | Codellama 70b Instruct | Llama 13b |
|---|---|---|
| LMArena Non-English | 992 | 819 |
Instruction Following Codellama 70b Instruct leads
Codellama 70b Instruct: 51.9 (#293), Llama 13b: 36.7 (#305)
| Benchmark | Codellama 70b Instruct | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1024 | 781 |
Writing & Preference Codellama 70b Instruct leads
Codellama 70b Instruct: 33.4 (#277), Llama 13b: 13.8 (#312)
| Benchmark | Codellama 70b Instruct | Llama 13b |
|---|---|---|
| LMArena Text | 1057 | 834 |
| LMArena Creative Writing | — | 794 |
| LMArena Multi-Turn | — | 753 |
Frequently asked questions
Is Codellama 70b Instruct better than Llama 13b?
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 24.4 on the Noometry Index.
Is Codellama 70b Instruct or Llama 13b better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 21.4 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Llama 13b share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Llama 13b has 21.