Model comparison
Codellama 70b Instruct vs Llama 3-70B
Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 28.5 on the Noometry Index.
Last verified . 7 shared benchmarks.
MetaSummary
- They share 7 benchmarks with published results for both. Codellama 70b Instruct scores higher in 2 categories and Llama 3-70B in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama 3-70B leads 62.8 to 52.1.
Side by side
| Codellama 70b Instruct | Llama 3-70B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 33.3 | 28.5 |
| Released | — | 2024-04-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 31 |
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 3-70B: 35.3 (#215)
| Benchmark | Codellama 70b Instruct | Llama 3-70B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 43.6% |
| BigCodeBench Complete | 49.6% | 54.5% |
| HumanEval+ | 65.9% | 72% |
| LMArena Coding | — | 1206 |
| MBPP+ | — | 69% |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, Llama 3-70B: 20.9 (#132)
| Benchmark | Codellama 70b Instruct | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning Codellama 70b Instruct leads
Codellama 70b Instruct: 19.2 (#241), Llama 3-70B: 17.4 (#284)
| Benchmark | Codellama 70b Instruct | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1195 |
| Kagi LLM Benchmark | — | 35.1% |
| DTBench | — | 54.2% |
| Epoch Capabilities Index | — | 122.91 |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |
Math Not comparable
Codellama 70b Instruct: —, Llama 3-70B: 12.0 (#299)
| Benchmark | Codellama 70b Instruct | Llama 3-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| LMArena Math | — | 1218 |
| MATH Level 5 | — | 22.6% |
Knowledge Not comparable
Codellama 70b Instruct: —, Llama 3-70B: 20.8 (#272)
| Benchmark | Codellama 70b Instruct | Llama 3-70B |
|---|---|---|
| GPQA Diamond | — | 40.6% |
| LMArena Expert | — | 1149 |
| MMLU | — | 79.3% |
Multilingual Llama 3-70B leads
Codellama 70b Instruct: 24.9 (#283), Llama 3-70B: 33.8 (#246)
| Benchmark | Codellama 70b Instruct | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 992 | 1142 |
| LMArena Chinese | — | 1114 |
| LMArena French | — | 1231 |
| LMArena German | — | 1169 |
| LMArena Japanese | — | 1017 |
| LMArena Korean | — | 1017 |
| LMArena Russian | — | 1159 |
| LMArena Spanish | — | 1241 |
Instruction Following Llama 3-70B leads
Codellama 70b Instruct: 52.1 (#288), Llama 3-70B: 62.8 (#233)
| Benchmark | Codellama 70b Instruct | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1194 |
Long Context Not comparable
Codellama 70b Instruct: —, Llama 3-70B: 35.6 (#235)
| Benchmark | Codellama 70b Instruct | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | — | 1174 |
Writing & Preference Llama 3-70B leads
Codellama 70b Instruct: 33.6 (#272), Llama 3-70B: 43.0 (#225)
| Benchmark | Codellama 70b Instruct | Llama 3-70B |
|---|---|---|
| LMArena Text | 1057 | 1221 |
| LMArena Creative Writing | — | 1210 |
| LMArena Multi-Turn | — | 1223 |
Frequently asked questions
Is Codellama 70b Instruct better than Llama 3-70B?
Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 28.5 on the Noometry Index.
Is Codellama 70b Instruct or Llama 3-70B better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.0 versus 35.3 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Llama 3-70B share?
7 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Llama 3-70B has 31.