Model comparison
Codellama 34b Instruct vs Codellama 70b Instruct
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 30.8 on the Noometry Index.
Last verified . 7 shared benchmarks.
MetaSummary
- They share 7 benchmarks with published results for both. Codellama 34b Instruct scores higher in 2 categories and Codellama 70b Instruct in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where Codellama 70b Instruct leads 37.6 to 28.5.
- The biggest single-benchmark swing is BigCodeBench Complete: 37.1% for Codellama 34b Instruct and 49.6% for Codellama 70b Instruct.
Side by side
| Codellama 34b Instruct | Codellama 70b Instruct | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 30.8 | 33.7 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 34b Instruct: 28.5 (#314), Codellama 70b Instruct: 37.6 (#193)
| Benchmark | Codellama 34b Instruct | Codellama 70b Instruct |
|---|---|---|
| BigCodeBench Instruct | 29% | 40.7% |
| BigCodeBench Complete | 37.1% | 49.6% |
| HumanEval+ | 43.9% | 65.9% |
| LMArena Coding | 1046 | — |
| MBPP+ | 56.3% | — |
Reasoning Too close to call
Codellama 34b Instruct: 19.6 (#255), Codellama 70b Instruct: 20.1 (#242)
| Benchmark | Codellama 34b Instruct | Codellama 70b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1052 |
Math Not comparable
Codellama 34b Instruct: 31.0 (#230), Codellama 70b Instruct: —
| Benchmark | Codellama 34b Instruct | Codellama 70b Instruct |
|---|---|---|
| LMArena Math | 1056 | — |
Multilingual Codellama 34b Instruct leads
Codellama 34b Instruct: 25.8 (#284), Codellama 70b Instruct: 24.8 (#288)
| Benchmark | Codellama 34b Instruct | Codellama 70b Instruct |
|---|---|---|
| LMArena Non-English | 1011 | 992 |
| LMArena Chinese | 976 | — |
Instruction Following Too close to call
Codellama 34b Instruct: 52.2 (#291), Codellama 70b Instruct: 51.9 (#293)
| Benchmark | Codellama 34b Instruct | Codellama 70b Instruct |
|---|---|---|
| LMArena Instruction Following | 1028 | 1024 |
Long Context Not comparable
Codellama 34b Instruct: 30.9 (#284), Codellama 70b Instruct: —
| Benchmark | Codellama 34b Instruct | Codellama 70b Instruct |
|---|---|---|
| LMArena Longer Query | 1013 | — |
Writing & Preference Codellama 70b Instruct leads
Codellama 34b Instruct: 28.2 (#297), Codellama 70b Instruct: 33.4 (#277)
| Benchmark | Codellama 34b Instruct | Codellama 70b Instruct |
|---|---|---|
| LMArena Text | 1066 | 1057 |
| LMArena Creative Writing | 1032 | — |
| LMArena Multi-Turn | 1015 | — |
Frequently asked questions
Is Codellama 34b Instruct better than Codellama 70b Instruct?
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or Codellama 70b Instruct better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Codellama 70b Instruct share?
7 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Codellama 70b Instruct has 7.