Model comparison
Codellama 70b Instruct vs Gemma 2B
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 29.6 on the Noometry Index.
Last verified . 5 shared benchmarks.
Meta
GoogleSummary
- They share 5 benchmarks with published results for both. Codellama 70b Instruct scores higher in 5 categories and Gemma 2B in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Codellama 70b Instruct leads 33.4 to 24.0.
Side by side
| Codellama 70b Instruct | Gemma 2B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 33.7 | 29.6 |
| Released | — | 2024-02-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 70b Instruct: 37.6 (#193), Gemma 2B: 29.4 (#305)
| Benchmark | Codellama 70b Instruct | Gemma 2B |
|---|---|---|
| HumanEval+ | 65.9% | 20.7% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1010 |
| BigCodeBench Complete | 49.6% | — |
| MBPP+ | — | 34.1% |
Reasoning Codellama 70b Instruct leads
Codellama 70b Instruct: 20.1 (#242), Gemma 2B: 18.8 (#275)
| Benchmark | Codellama 70b Instruct | Gemma 2B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 989 |
| BIG-Bench Hard | — | 35.2% |
| Epoch Capabilities Index | — | 94.2 |
| HellaSwag | — | 71.4% |
| PIQA | — | 77.3% |
| WinoGrande | — | 65.4% |
Math Not comparable
Codellama 70b Instruct: —, Gemma 2B: 30.0 (#239)
| Benchmark | Codellama 70b Instruct | Gemma 2B |
|---|---|---|
| LMArena Math | — | 1009 |
| GSM8K | — | 17.7% |
Knowledge Not comparable
Codellama 70b Instruct: —, Gemma 2B: —
| Benchmark | Codellama 70b Instruct | Gemma 2B |
|---|---|---|
| ARC (AI2) Challenge | — | 42.1% |
| BoolQ | — | 69.4% |
| MMLU | — | 42.3% |
| TriviaQA | — | 53.2% |
Multilingual Codellama 70b Instruct leads
Codellama 70b Instruct: 24.8 (#288), Gemma 2B: 23.0 (#294)
| Benchmark | Codellama 70b Instruct | Gemma 2B |
|---|---|---|
| LMArena Non-English | 992 | 958 |
| LMArena Chinese | — | 986 |
| LMArena Russian | — | 937 |
Instruction Following Codellama 70b Instruct leads
Codellama 70b Instruct: 51.9 (#293), Gemma 2B: 48.5 (#302)
| Benchmark | Codellama 70b Instruct | Gemma 2B |
|---|---|---|
| LMArena Instruction Following | 1024 | 970 |
Long Context Not comparable
Codellama 70b Instruct: —, Gemma 2B: 29.9 (#291)
| Benchmark | Codellama 70b Instruct | Gemma 2B |
|---|---|---|
| LMArena Longer Query | — | 981 |
Writing & Preference Codellama 70b Instruct leads
Codellama 70b Instruct: 33.4 (#277), Gemma 2B: 24.0 (#308)
| Benchmark | Codellama 70b Instruct | Gemma 2B |
|---|---|---|
| LMArena Text | 1057 | 1002 |
| LMArena Creative Writing | — | 987 |
| LMArena Multi-Turn | — | 945 |
Frequently asked questions
Is Codellama 70b Instruct better than Gemma 2B?
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 29.6 on the Noometry Index.
Is Codellama 70b Instruct or Gemma 2B better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 29.4 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Gemma 2B share?
5 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Gemma 2B has 23.