Model comparison
Codellama 34b Instruct vs Gemma 2 27B
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 29.4 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 2 categories and Gemma 2 27B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Codellama 34b Instruct leads 31.0 to 10.7.
- The biggest single-benchmark swing is BigCodeBench Complete: 37.1% for Codellama 34b Instruct and 52.5% for Gemma 2 27B.
Side by side
| Codellama 34b Instruct | Gemma 2 27B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 30.8 | 29.4 |
| Released | — | 2024-06-24 |
| Weights | Open | Open |
| Context window | — | 8K |
| Max output | — | 2K |
| Input $ / M tokens | — | $0.65 |
| Output $ / M tokens | — | $0.65 |
| Results tracked | 14 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2 27B leads
Codellama 34b Instruct: 28.5 (#314), Gemma 2 27B: 34.1 (#246)
| Benchmark | Codellama 34b Instruct | Gemma 2 27B |
|---|---|---|
| BigCodeBench Instruct | 29% | 42.8% |
| LMArena Coding | 1046 | 1211 |
| BigCodeBench Complete | 37.1% | 52.5% |
| LiveBench Coding | — | 36% |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning Codellama 34b Instruct leads
Codellama 34b Instruct: 19.6 (#255), Gemma 2 27B: 15.3 (#315)
| Benchmark | Codellama 34b Instruct | Gemma 2 27B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1198 |
| LiveBench Reasoning | — | 28.1% |
| DTBench | — | 48% |
| LiveBench Data Analysis | — | 47.9% |
| LMCA | — | 7.1% |
| Epoch Capabilities Index | — | 122.08 |
| LiveBench | — | 38.2% |
Math Codellama 34b Instruct leads
Codellama 34b Instruct: 31.0 (#230), Gemma 2 27B: 10.7 (#311)
| Benchmark | Codellama 34b Instruct | Gemma 2 27B |
|---|---|---|
| LMArena Math | 1056 | 1212 |
| OTIS Mock AIME 2024-2025 | — | 1.4% |
| LiveBench Math | — | 26.5% |
| MATH Level 5 | — | 27.9% |
Knowledge Not comparable
Codellama 34b Instruct: —, Gemma 2 27B: 19.0 (#280)
| Benchmark | Codellama 34b Instruct | Gemma 2 27B |
|---|---|---|
| GPQA Diamond | — | 36.5% |
| Confabulations | — | 27.1% |
| LMArena Expert | — | 1172 |
| MMLU | — | 75.7% |
Multilingual Gemma 2 27B leads
Codellama 34b Instruct: 25.8 (#284), Gemma 2 27B: 38.6 (#226)
| Benchmark | Codellama 34b Instruct | Gemma 2 27B |
|---|---|---|
| LMArena Non-English | 1011 | 1217 |
| LMArena Chinese | 976 | 1221 |
| LMArena French | — | 1247 |
| LMArena German | — | 1209 |
| LMArena Japanese | — | 1175 |
| LMArena Korean | — | 1174 |
| LMArena Russian | — | 1234 |
| LMArena Spanish | — | 1228 |
Instruction Following Gemma 2 27B leads
Codellama 34b Instruct: 52.2 (#291), Gemma 2 27B: 60.5 (#249)
| Benchmark | Codellama 34b Instruct | Gemma 2 27B |
|---|---|---|
| LMArena Instruction Following | 1028 | 1206 |
| LiveBench Instruction Following | — | 58.1% |
Long Context Gemma 2 27B leads
Codellama 34b Instruct: 30.9 (#284), Gemma 2 27B: 37.3 (#218)
| Benchmark | Codellama 34b Instruct | Gemma 2 27B |
|---|---|---|
| LMArena Longer Query | 1013 | 1231 |
Writing & Preference Gemma 2 27B leads
Codellama 34b Instruct: 28.2 (#297), Gemma 2 27B: 44.2 (#225)
| Benchmark | Codellama 34b Instruct | Gemma 2 27B |
|---|---|---|
| LMArena Text | 1066 | 1231 |
| LMArena Creative Writing | 1032 | 1241 |
| LMArena Multi-Turn | 1015 | 1224 |
| LiveBench Language | — | 32.6% |
Frequently asked questions
Is Codellama 34b Instruct better than Gemma 2 27B?
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 29.4 on the Noometry Index.
Is Codellama 34b Instruct or Gemma 2 27B better for coding?
Gemma 2 27B scores higher on coding benchmarks: 34.1 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Gemma 2 27B share?
12 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Gemma 2 27B has 34.