Model comparison
Codellama 34b Instruct vs Llama 3-70B
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 28.8 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 3-70B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Codellama 34b Instruct leads 31.0 to 12.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 37.1% for Codellama 34b Instruct and 54.5% for Llama 3-70B.
Side by side
| Codellama 34b Instruct | Llama 3-70B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 30.8 | 28.8 |
| Released | — | 2024-04-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Codellama 34b Instruct: 28.5 (#314), Llama 3-70B: 35.8 (#218)
| Benchmark | Codellama 34b Instruct | Llama 3-70B |
|---|---|---|
| BigCodeBench Instruct | 29% | 43.6% |
| LMArena Coding | 1046 | 1206 |
| BigCodeBench Complete | 37.1% | 54.5% |
| HumanEval+ | 43.9% | 72% |
| MBPP+ | 56.3% | 69% |
Agentic & Tool Use Not comparable
Codellama 34b Instruct: —, Llama 3-70B: 21.1 (#139)
| Benchmark | Codellama 34b Instruct | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning Codellama 34b Instruct leads
Codellama 34b Instruct: 19.6 (#255), Llama 3-70B: 18.0 (#288)
| Benchmark | Codellama 34b Instruct | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1195 |
| Kagi LLM Benchmark | — | 35.1% |
| DTBench | — | 54.2% |
| Epoch Capabilities Index | — | 122.93 |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |
Math Codellama 34b Instruct leads
Codellama 34b Instruct: 31.0 (#230), Llama 3-70B: 12.8 (#305)
| Benchmark | Codellama 34b Instruct | Llama 3-70B |
|---|---|---|
| LMArena Math | 1056 | 1218 |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| MATH Level 5 | — | 22.6% |
Knowledge Not comparable
Codellama 34b Instruct: —, Llama 3-70B: 20.8 (#277)
| Benchmark | Codellama 34b Instruct | Llama 3-70B |
|---|---|---|
| GPQA Diamond | — | 40.6% |
| LMArena Expert | — | 1149 |
| MMLU | — | 79.3% |
Multilingual Llama 3-70B leads
Codellama 34b Instruct: 25.8 (#284), Llama 3-70B: 33.6 (#251)
| Benchmark | Codellama 34b Instruct | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1011 | 1142 |
| LMArena Chinese | 976 | 1114 |
| LMArena French | — | 1232 |
| LMArena German | — | 1169 |
| LMArena Japanese | — | 1017 |
| LMArena Korean | — | 1017 |
| LMArena Russian | — | 1159 |
| LMArena Spanish | — | 1241 |
Instruction Following Llama 3-70B leads
Codellama 34b Instruct: 52.2 (#291), Llama 3-70B: 62.5 (#238)
| Benchmark | Codellama 34b Instruct | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1028 | 1194 |
Long Context Llama 3-70B leads
Codellama 34b Instruct: 30.9 (#284), Llama 3-70B: 35.6 (#240)
| Benchmark | Codellama 34b Instruct | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1013 | 1174 |
Writing & Preference Llama 3-70B leads
Codellama 34b Instruct: 28.2 (#297), Llama 3-70B: 42.8 (#231)
| Benchmark | Codellama 34b Instruct | Llama 3-70B |
|---|---|---|
| LMArena Text | 1066 | 1221 |
| LMArena Creative Writing | 1032 | 1210 |
| LMArena Multi-Turn | 1015 | 1223 |
Frequently asked questions
Is Codellama 34b Instruct better than Llama 3-70B?
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 28.8 on the Noometry Index.
Is Codellama 34b Instruct or Llama 3-70B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.8 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Llama 3-70B share?
14 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Llama 3-70B has 31.