Model comparison
Gemma 2 27B vs Llama 13b
Gemma 2 27B is the stronger model overall, scoring 29.2 to 23.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
Google
MetaSummary
- They share 10 benchmarks with published results for both. Gemma 2 27B scores higher in 5 categories and Llama 13b in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 2 27B leads 44.4 to 13.9.
Side by side
| Gemma 2 27B | Llama 13b | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 29.2 | 23.9 |
| Released | 2024-06-24 | 2023-02-24 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 2K | — |
| Input $ / M tokens | $0.65 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 34 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2 27B leads
Gemma 2 27B: 33.5 (#243), Llama 13b: 20.9 (#332)
| Benchmark | Gemma 2 27B | Llama 13b |
|---|---|---|
| LMArena Coding | 1211 | 683 |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |
Reasoning Gemma 2 27B leads
Gemma 2 27B: 14.8 (#313), Llama 13b: 13.4 (#327)
| Benchmark | Gemma 2 27B | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1199 | 728 |
| Epoch Capabilities Index | 122.06 | 100.09 |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 48% | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| BIG-Bench Hard | — | 37.9% |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| LiveBench | 38.2% | — |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |
Math Llama 13b leads
Gemma 2 27B: 10.0 (#306), Llama 13b: 24.4 (#259)
| Benchmark | Gemma 2 27B | Llama 13b |
|---|---|---|
| LMArena Math | 1212 | 838 |
| OTIS Mock AIME 2024-2025 | 1.4% | — |
| LiveBench Math | 26.5% | — |
| MATH Level 5 | 27.9% | — |
| GSM8K | — | 20.6% |
Knowledge Not comparable
Gemma 2 27B: 18.9 (#275), Llama 13b: —
| Benchmark | Gemma 2 27B | Llama 13b |
|---|---|---|
| MMLU | 75.7% | 47.7% |
| GPQA Diamond | 36.5% | — |
| Confabulations | 27.1% | — |
| LMArena Expert | 1172 | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
Gemma 2 27B: —, Llama 13b: —
| Benchmark | Gemma 2 27B | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |
Multilingual Gemma 2 27B leads
Gemma 2 27B: 38.8 (#221), Llama 13b: 16.8 (#292)
| Benchmark | Gemma 2 27B | Llama 13b |
|---|---|---|
| LMArena Non-English | 1217 | 819 |
| LMArena Chinese | 1221 | — |
| LMArena French | 1246 | — |
| LMArena German | 1209 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1174 | — |
| LMArena Russian | 1234 | — |
| LMArena Spanish | 1228 | — |
Instruction Following Gemma 2 27B leads
Gemma 2 27B: 60.7 (#244), Llama 13b: 36.9 (#300)
| Benchmark | Gemma 2 27B | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1206 | 781 |
| LiveBench Instruction Following | 58.1% | — |
Long Context Not comparable
Gemma 2 27B: 37.3 (#213), Llama 13b: —
| Benchmark | Gemma 2 27B | Llama 13b |
|---|---|---|
| LMArena Longer Query | 1231 | — |
Writing & Preference Gemma 2 27B leads
Gemma 2 27B: 44.4 (#220), Llama 13b: 13.9 (#307)
| Benchmark | Gemma 2 27B | Llama 13b |
|---|---|---|
| LMArena Text | 1231 | 834 |
| LMArena Creative Writing | 1241 | 794 |
| LMArena Multi-Turn | 1224 | 753 |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than Llama 13b?
Gemma 2 27B is the stronger model overall, scoring 29.2 to 23.9 on the Noometry Index.
Is Gemma 2 27B or Llama 13b better for coding?
Gemma 2 27B scores higher on coding benchmarks: 33.5 versus 20.9 in the Noometry coding category.
How many benchmarks do Gemma 2 27B and Llama 13b share?
10 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Llama 13b has 21.