Model comparison
Codellama 34b Instruct vs Llama 3-8B
Codellama 34b Instruct is the stronger model overall, scoring 30.2 to 25.3 on the Noometry Index.
Last verified . 14 shared benchmarks.
MetaSummary
- They share 14 benchmarks with published results for both. Codellama 34b Instruct scores higher in 2 categories and Llama 3-8B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Codellama 34b Instruct leads 28.5 to 8.3.
Side by side
| Codellama 34b Instruct | Llama 3-8B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 30.2 | 25.3 |
| Released | — | 2024-04-18 |
| Weights | Open | Open |
| Context window | — | 8K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.14 |
| Output $ / M tokens | — | $0.14 |
| Results tracked | 14 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-8B leads
Codellama 34b Instruct: 28.0 (#310), Llama 3-8B: 30.5 (#285)
| Benchmark | Codellama 34b Instruct | Llama 3-8B |
|---|---|---|
| BigCodeBench Instruct | 29% | 31.9% |
| LMArena Coding | 1046 | 1152 |
| BigCodeBench Complete | 37.1% | 36.9% |
| HumanEval+ | 43.9% | 56.7% |
| MBPP+ | 56.3% | 54.8% |
Reasoning Codellama 34b Instruct leads
Codellama 34b Instruct: 18.8 (#250), Llama 3-8B: 13.8 (#321)
| Benchmark | Codellama 34b Instruct | Llama 3-8B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1133 |
| Chess Puzzles | — | 0% |
| DTBench | — | 43.9% |
| Adversarial NLI | — | 57.3% |
| Epoch Capabilities Index | — | 116.33 |
| ForecastBench | — | 58.6 |
| WinoGrande | — | 75.7% |
Math Codellama 34b Instruct leads
Codellama 34b Instruct: 28.5 (#227), Llama 3-8B: 8.3 (#317)
| Benchmark | Codellama 34b Instruct | Llama 3-8B |
|---|---|---|
| LMArena Math | 1056 | 1151 |
| OTIS Mock AIME 2024-2025 | — | 1.9% |
| MATH Level 5 | — | 6.1% |
Knowledge Not comparable
Codellama 34b Instruct: —, Llama 3-8B: 7.8 (#303)
| Benchmark | Codellama 34b Instruct | Llama 3-8B |
|---|---|---|
| GPQA Diamond | — | 26.1% |
| LMArena Expert | — | 1113 |
| ARC (AI2) Challenge | — | 82.8% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 82.6% |
| TriviaQA | — | 67.7% |
Multilingual Llama 3-8B leads
Codellama 34b Instruct: 25.9 (#279), Llama 3-8B: 31.0 (#256)
| Benchmark | Codellama 34b Instruct | Llama 3-8B |
|---|---|---|
| LMArena Non-English | 1011 | 1098 |
| LMArena Chinese | 976 | 1076 |
| LMArena French | — | 1158 |
| LMArena German | — | 1104 |
| LMArena Japanese | — | 967 |
| LMArena Korean | — | 1003 |
| LMArena Russian | — | 1109 |
| LMArena Spanish | — | 1172 |
Instruction Following Llama 3-8B leads
Codellama 34b Instruct: 52.4 (#286), Llama 3-8B: 58.7 (#255)
| Benchmark | Codellama 34b Instruct | Llama 3-8B |
|---|---|---|
| LMArena Instruction Following | 1028 | 1127 |
Long Context Llama 3-8B leads
Codellama 34b Instruct: 30.8 (#279), Llama 3-8B: 34.2 (#246)
| Benchmark | Codellama 34b Instruct | Llama 3-8B |
|---|---|---|
| LMArena Longer Query | 1014 | 1128 |
Writing & Preference Llama 3-8B leads
Codellama 34b Instruct: 28.4 (#292), Llama 3-8B: 37.7 (#251)
| Benchmark | Codellama 34b Instruct | Llama 3-8B |
|---|---|---|
| LMArena Text | 1066 | 1166 |
| LMArena Creative Writing | 1032 | 1150 |
| LMArena Multi-Turn | 1015 | 1152 |
Frequently asked questions
Is Codellama 34b Instruct better than Llama 3-8B?
Codellama 34b Instruct is the stronger model overall, scoring 30.2 to 25.3 on the Noometry Index.
Is Codellama 34b Instruct or Llama 3-8B better for coding?
Llama 3-8B scores higher on coding benchmarks: 30.5 versus 28.0 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Llama 3-8B share?
14 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Llama 3-8B has 34.