Model comparison
Codellama 34b Instruct vs Gemma 2B
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 29.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
Meta
GoogleSummary
- They share 12 benchmarks with published results for both. Codellama 34b Instruct scores higher in 6 categories and Gemma 2B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Codellama 34b Instruct leads 28.2 to 24.0.
Side by side
| Codellama 34b Instruct | Gemma 2B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 30.8 | 29.6 |
| Released | — | 2024-02-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Codellama 34b Instruct: 28.5 (#314), Gemma 2B: 29.4 (#305)
| Benchmark | Codellama 34b Instruct | Gemma 2B |
|---|---|---|
| LMArena Coding | 1046 | 1010 |
| HumanEval+ | 43.9% | 20.7% |
| MBPP+ | 56.3% | 34.1% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
Reasoning Too close to call
Codellama 34b Instruct: 19.6 (#255), Gemma 2B: 18.8 (#275)
| Benchmark | Codellama 34b Instruct | Gemma 2B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 989 |
| BIG-Bench Hard | — | 35.2% |
| Epoch Capabilities Index | — | 94.2 |
| HellaSwag | — | 71.4% |
| PIQA | — | 77.3% |
| WinoGrande | — | 65.4% |
Math Too close to call
Codellama 34b Instruct: 31.0 (#230), Gemma 2B: 30.0 (#239)
| Benchmark | Codellama 34b Instruct | Gemma 2B |
|---|---|---|
| LMArena Math | 1056 | 1009 |
| GSM8K | — | 17.7% |
Knowledge Not comparable
Codellama 34b Instruct: —, Gemma 2B: —
| Benchmark | Codellama 34b Instruct | Gemma 2B |
|---|---|---|
| ARC (AI2) Challenge | — | 42.1% |
| BoolQ | — | 69.4% |
| MMLU | — | 42.3% |
| TriviaQA | — | 53.2% |
Multilingual Codellama 34b Instruct leads
Codellama 34b Instruct: 25.8 (#284), Gemma 2B: 23.0 (#294)
| Benchmark | Codellama 34b Instruct | Gemma 2B |
|---|---|---|
| LMArena Non-English | 1011 | 958 |
| LMArena Chinese | 976 | 986 |
| LMArena Russian | — | 937 |
Instruction Following Codellama 34b Instruct leads
Codellama 34b Instruct: 52.2 (#291), Gemma 2B: 48.5 (#302)
| Benchmark | Codellama 34b Instruct | Gemma 2B |
|---|---|---|
| LMArena Instruction Following | 1028 | 970 |
Long Context Too close to call
Codellama 34b Instruct: 30.9 (#284), Gemma 2B: 29.9 (#291)
| Benchmark | Codellama 34b Instruct | Gemma 2B |
|---|---|---|
| LMArena Longer Query | 1013 | 981 |
Writing & Preference Codellama 34b Instruct leads
Codellama 34b Instruct: 28.2 (#297), Gemma 2B: 24.0 (#308)
| Benchmark | Codellama 34b Instruct | Gemma 2B |
|---|---|---|
| LMArena Text | 1066 | 1002 |
| LMArena Creative Writing | 1032 | 987 |
| LMArena Multi-Turn | 1015 | 945 |
Frequently asked questions
Is Codellama 34b Instruct better than Gemma 2B?
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 29.6 on the Noometry Index.
Is Codellama 34b Instruct or Gemma 2B better for coding?
They score almost the same on coding (28.5 vs 29.4); test both on your own repository before choosing.
How many benchmarks do Codellama 34b Instruct and Gemma 2B share?
12 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Gemma 2B has 23.