Model comparison
Codellama 34b Instruct vs Llama 2-7B
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 29.1 on the Noometry Index.
Last verified . 10 shared benchmarks.
MetaSummary
- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 6 categories and Llama 2-7B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Codellama 34b Instruct leads 19.6 to 15.7.
Side by side
| Codellama 34b Instruct | Llama 2-7B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 30.8 | 29.1 |
| Released | — | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 29 |
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), Llama 2-7B: 29.2 (#307)
| Benchmark | Codellama 34b Instruct | Llama 2-7B |
|---|---|---|
| LMArena Coding | 1046 | 1002 |
| 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 2-7B: 15.7 (#312)
| Benchmark | Codellama 34b Instruct | Llama 2-7B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1009 |
| Chess Puzzles | — | 0% |
| BIG-Bench Hard | — | 39.2% |
| Epoch Capabilities Index | — | 99.06 |
| HellaSwag | — | 77.2% |
| LAMBADA | — | 73.3% |
| PIQA | — | 78.8% |
| WinoGrande | — | 69.2% |
Math Too close to call
Codellama 34b Instruct: 31.0 (#230), Llama 2-7B: 30.7 (#233)
| Benchmark | Codellama 34b Instruct | Llama 2-7B |
|---|---|---|
| LMArena Math | 1056 | 1042 |
| GSM8K | — | 16.7% |
Knowledge Not comparable
Codellama 34b Instruct: —, Llama 2-7B: 28.2 (#248)
| Benchmark | Codellama 34b Instruct | Llama 2-7B |
|---|---|---|
| LMArena Expert | — | 1036 |
| ARC (AI2) Challenge | — | 45.9% |
| BoolQ | — | 77.9% |
| MMLU | — | 45.8% |
| OpenBookQA | — | 58.6% |
| TriviaQA | — | 73.7% |
Multimodal Not comparable
Codellama 34b Instruct: —, Llama 2-7B: —
| Benchmark | Codellama 34b Instruct | Llama 2-7B |
|---|---|---|
| ScienceQA | — | 43.1% |
Multilingual Codellama 34b Instruct leads
Codellama 34b Instruct: 25.8 (#284), Llama 2-7B: 23.8 (#293)
| Benchmark | Codellama 34b Instruct | Llama 2-7B |
|---|---|---|
| LMArena Non-English | 1011 | 973 |
| LMArena Chinese | 976 | 973 |
| LMArena French | — | 970 |
| LMArena German | — | 978 |
| LMArena Russian | — | 995 |
| LMArena Spanish | — | 1007 |
Instruction Following Codellama 34b Instruct leads
Codellama 34b Instruct: 52.2 (#291), Llama 2-7B: 50.8 (#298)
| Benchmark | Codellama 34b Instruct | Llama 2-7B |
|---|---|---|
| LMArena Instruction Following | 1028 | 1006 |
Long Context Too close to call
Codellama 34b Instruct: 30.9 (#284), Llama 2-7B: 30.4 (#287)
| Benchmark | Codellama 34b Instruct | Llama 2-7B |
|---|---|---|
| LMArena Longer Query | 1013 | 999 |
Writing & Preference Too close to call
Codellama 34b Instruct: 28.2 (#297), Llama 2-7B: 28.0 (#298)
| Benchmark | Codellama 34b Instruct | Llama 2-7B |
|---|---|---|
| LMArena Text | 1066 | 1053 |
| LMArena Creative Writing | 1032 | 1033 |
| LMArena Multi-Turn | 1015 | 1029 |
Frequently asked questions
Is Codellama 34b Instruct better than Llama 2-7B?
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 29.1 on the Noometry Index.
Is Codellama 34b Instruct or Llama 2-7B better for coding?
They score almost the same on coding (28.5 vs 29.2); test both on your own repository before choosing.
How many benchmarks do Codellama 34b Instruct and Llama 2-7B share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Llama 2-7B has 29.