Model comparison
Codellama 34b Instruct vs Llama 2-70B
Codellama 34b Instruct is the stronger model overall, scoring 30.2 to 24.1 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 2 categories and Llama 2-70B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Codellama 34b Instruct leads 28.5 to 7.5.
Side by side
| Codellama 34b Instruct | Llama 2-70B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 30.2 | 24.1 |
| Released | — | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-70B leads
Codellama 34b Instruct: 28.0 (#310), Llama 2-70B: 30.8 (#281)
| Benchmark | Codellama 34b Instruct | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1046 | 1079 |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning Codellama 34b Instruct leads
Codellama 34b Instruct: 18.8 (#250), Llama 2-70B: 13.7 (#324)
| Benchmark | Codellama 34b Instruct | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1073 |
| DTBench | — | 41.6% |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| Epoch Capabilities Index | — | 113.59 |
| ForecastBench | — | 51.4 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |
Math Codellama 34b Instruct leads
Codellama 34b Instruct: 28.5 (#227), Llama 2-70B: 7.5 (#320)
| Benchmark | Codellama 34b Instruct | Llama 2-70B |
|---|---|---|
| LMArena Math | 1056 | 1091 |
| OTIS Mock AIME 2024-2025 | — | 0% |
| MATH Level 5 | — | 3.3% |
| GSM8K | — | 69.6% |
Knowledge Not comparable
Codellama 34b Instruct: —, Llama 2-70B: 7.4 (#305)
| Benchmark | Codellama 34b Instruct | Llama 2-70B |
|---|---|---|
| GPQA Diamond | — | 26.3% |
| LMArena Expert | — | 1039 |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |
Multilingual Llama 2-70B leads
Codellama 34b Instruct: 25.9 (#279), Llama 2-70B: 27.9 (#269)
| Benchmark | Codellama 34b Instruct | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1011 | 1045 |
| LMArena Chinese | 976 | 994 |
| LMArena French | — | 1089 |
| LMArena German | — | 1041 |
| LMArena Japanese | — | 927 |
| LMArena Korean | — | 964 |
| LMArena Russian | — | 1083 |
| LMArena Spanish | — | 1142 |
Instruction Following Llama 2-70B leads
Codellama 34b Instruct: 52.4 (#286), Llama 2-70B: 55.1 (#273)
| Benchmark | Codellama 34b Instruct | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1028 | 1071 |
Long Context Llama 2-70B leads
Codellama 34b Instruct: 30.8 (#279), Llama 2-70B: 32.2 (#265)
| Benchmark | Codellama 34b Instruct | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1014 | 1062 |
Writing & Preference Llama 2-70B leads
Codellama 34b Instruct: 28.4 (#292), Llama 2-70B: 32.5 (#274)
| Benchmark | Codellama 34b Instruct | Llama 2-70B |
|---|---|---|
| LMArena Text | 1066 | 1115 |
| LMArena Creative Writing | 1032 | 1075 |
| LMArena Multi-Turn | 1015 | 1088 |
Frequently asked questions
Is Codellama 34b Instruct better than Llama 2-70B?
Codellama 34b Instruct is the stronger model overall, scoring 30.2 to 24.1 on the Noometry Index.
Is Codellama 34b Instruct or Llama 2-70B better for coding?
Llama 2-70B scores higher on coding benchmarks: 30.8 versus 28.0 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Llama 2-70B share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Llama 2-70B has 35.