Model comparison
Codellama 70b Instruct vs Gemma 2 9B
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 25.9 on the Noometry Index.
Last verified . 6 shared benchmarks.
Meta
GoogleSummary
- They share 6 benchmarks with published results for both. Codellama 70b Instruct scores higher in 3 categories and Gemma 2 9B in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemma 2 9B leads 36.6 to 24.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 49.6% for Codellama 70b Instruct and 40.6% for Gemma 2 9B.
Side by side
| Codellama 70b Instruct | Gemma 2 9B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 33.7 | 25.9 |
| Released | — | 2024-06-24 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 35 |
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 2 9B: 29.4 (#304)
| Benchmark | Codellama 70b Instruct | Gemma 2 9B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 34.7% |
| BigCodeBench Complete | 49.6% | 40.6% |
| LiveBench Coding | — | 22.5% |
| LMArena Coding | — | 1173 |
| HumanEval+ | 65.9% | — |
Reasoning Codellama 70b Instruct leads
Codellama 70b Instruct: 20.1 (#242), Gemma 2 9B: 15.9 (#309)
| Benchmark | Codellama 70b Instruct | Gemma 2 9B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1171 |
| LiveBench Reasoning | — | 15.2% |
| LiveBench Data Analysis | — | 36.4% |
| Epoch Capabilities Index | — | 119.83 |
| LiveBench | — | 28.7% |
| PIQA | — | 83.7% |
Math Not comparable
Codellama 70b Instruct: —, Gemma 2 9B: 9.9 (#318)
| Benchmark | Codellama 70b Instruct | Gemma 2 9B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 0.6% |
| LiveBench Math | — | 19.8% |
| LMArena Math | — | 1183 |
| MATH Level 5 | — | 21% |
| GSM8K | — | 84.9% |
Knowledge Not comparable
Codellama 70b Instruct: —, Gemma 2 9B: 9.7 (#305)
| Benchmark | Codellama 70b Instruct | Gemma 2 9B |
|---|---|---|
| GPQA Diamond | — | 27.5% |
| LMArena Expert | — | 1147 |
| BoolQ | — | 85.7% |
| MMLU | — | 72.1% |
Multilingual Gemma 2 9B leads
Codellama 70b Instruct: 24.8 (#288), Gemma 2 9B: 36.6 (#238)
| Benchmark | Codellama 70b Instruct | Gemma 2 9B |
|---|---|---|
| LMArena Non-English | 992 | 1188 |
| LMArena Chinese | — | 1185 |
| LMArena French | — | 1190 |
| LMArena German | — | 1186 |
| LMArena Japanese | — | 1144 |
| LMArena Korean | — | 1137 |
| LMArena Russian | — | 1200 |
| LMArena Spanish | — | 1200 |
Instruction Following Gemma 2 9B leads
Codellama 70b Instruct: 51.9 (#293), Gemma 2 9B: 57.6 (#269)
| Benchmark | Codellama 70b Instruct | Gemma 2 9B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1178 |
| LiveBench Instruction Following | — | 52.6% |
Long Context Not comparable
Codellama 70b Instruct: —, Gemma 2 9B: 36.3 (#233)
| Benchmark | Codellama 70b Instruct | Gemma 2 9B |
|---|---|---|
| LMArena Longer Query | — | 1197 |
Writing & Preference Codellama 70b Instruct leads
Codellama 70b Instruct: 33.4 (#277), Gemma 2 9B: 32.1 (#281)
| Benchmark | Codellama 70b Instruct | Gemma 2 9B |
|---|---|---|
| LMArena Text | 1057 | 1207 |
| LMArena Creative Writing | — | 1206 |
| EQ-Bench Creative Writing | — | 841 |
| LMArena Multi-Turn | — | 1193 |
| LiveBench Language | — | 25.5% |
Frequently asked questions
Is Codellama 70b Instruct better than Gemma 2 9B?
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 25.9 on the Noometry Index.
Is Codellama 70b Instruct or Gemma 2 9B 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 2 9B share?
6 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Gemma 2 9B has 35.