Model comparison
Codellama 70b Instruct vs Llama 2-13B
Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 29.1 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 3 categories and Llama 2-13B in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Codellama 70b Instruct leads 19.2 to 12.3.
Side by side
| Codellama 70b Instruct | Llama 2-13B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 33.3 | 29.1 |
| Released | — | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 70b Instruct: 37.0 (#189), Llama 2-13B: 30.4 (#287)
| Benchmark | Codellama 70b Instruct | Llama 2-13B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1062 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning Codellama 70b Instruct leads
Codellama 70b Instruct: 19.2 (#241), Llama 2-13B: 12.3 (#333)
| Benchmark | Codellama 70b Instruct | Llama 2-13B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1051 |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.2% |
| BIG-Bench Hard | — | 58.2% |
| Epoch Capabilities Index | — | 105.8 |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math Not comparable
Codellama 70b Instruct: —, Llama 2-13B: 28.7 (#226)
| Benchmark | Codellama 70b Instruct | Llama 2-13B |
|---|---|---|
| LMArena Math | — | 1065 |
| GSM8K | — | 36.9% |
Knowledge Not comparable
Codellama 70b Instruct: —, Llama 2-13B: 27.5 (#244)
| Benchmark | Codellama 70b Instruct | Llama 2-13B |
|---|---|---|
| LMArena Expert | — | 1030 |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
Codellama 70b Instruct: —, Llama 2-13B: —
| Benchmark | Codellama 70b Instruct | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |
Multilingual Llama 2-13B leads
Codellama 70b Instruct: 24.9 (#283), Llama 2-13B: 26.7 (#274)
| Benchmark | Codellama 70b Instruct | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 992 | 1024 |
| LMArena Chinese | — | 1001 |
| LMArena French | — | 1043 |
| LMArena German | — | 1009 |
| LMArena Japanese | — | 894 |
| LMArena Korean | — | 953 |
| LMArena Russian | — | 1055 |
| LMArena Spanish | — | 1086 |
Instruction Following Llama 2-13B leads
Codellama 70b Instruct: 52.1 (#288), Llama 2-13B: 53.5 (#282)
| Benchmark | Codellama 70b Instruct | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1046 |
Long Context Not comparable
Codellama 70b Instruct: —, Llama 2-13B: 32.3 (#264)
| Benchmark | Codellama 70b Instruct | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | — | 1064 |
Writing & Preference Codellama 70b Instruct leads
Codellama 70b Instruct: 33.6 (#272), Llama 2-13B: 30.0 (#284)
| Benchmark | Codellama 70b Instruct | Llama 2-13B |
|---|---|---|
| LMArena Text | 1057 | 1085 |
| LMArena Creative Writing | — | 1047 |
| LMArena Multi-Turn | — | 1050 |
Frequently asked questions
Is Codellama 70b Instruct better than Llama 2-13B?
Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 29.1 on the Noometry Index.
Is Codellama 70b Instruct or Llama 2-13B better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.0 versus 30.4 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Llama 2-13B share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Llama 2-13B has 32.