Model comparison
Gemma 2 9B vs Llama 13b
Gemma 2 9B is the stronger model overall, scoring 25.9 to 24.4 on the Noometry Index.
Last verified . 13 shared benchmarks.
Google
MetaSummary
- They share 13 benchmarks with published results for both. Gemma 2 9B scores higher in 5 categories and Llama 13b in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Gemma 2 9B leads 57.6 to 36.7.
Side by side
| Gemma 2 9B | Llama 13b | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 25.9 | 24.4 |
| Released | 2024-06-24 | 2023-02-24 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2 9B leads
Gemma 2 9B: 29.4 (#304), Llama 13b: 21.4 (#337)
| Benchmark | Gemma 2 9B | Llama 13b |
|---|---|---|
| LMArena Coding | 1173 | 683 |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
Reasoning Gemma 2 9B leads
Gemma 2 9B: 15.9 (#309), Llama 13b: 14.0 (#329)
| Benchmark | Gemma 2 9B | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1171 | 728 |
| Epoch Capabilities Index | 119.83 | 100.58 |
| PIQA | 83.7% | 80.1% |
| LiveBench Reasoning | 15.2% | — |
| LiveBench Data Analysis | 36.4% | — |
| BIG-Bench Hard | — | 37.9% |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| LiveBench | 28.7% | — |
| WinoGrande | — | 73% |
Math Llama 13b leads
Gemma 2 9B: 9.9 (#318), Llama 13b: 26.7 (#256)
| Benchmark | Gemma 2 9B | Llama 13b |
|---|---|---|
| LMArena Math | 1183 | 838 |
| GSM8K | 84.9% | 20.6% |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
Knowledge Not comparable
Gemma 2 9B: 9.7 (#305), Llama 13b: —
| Benchmark | Gemma 2 9B | Llama 13b |
|---|---|---|
| BoolQ | 85.7% | 78.7% |
| MMLU | 72.1% | 47.7% |
| GPQA Diamond | 27.5% | — |
| LMArena Expert | 1147 | — |
| ARC (AI2) Challenge | — | 52.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
Gemma 2 9B: —, Llama 13b: —
| Benchmark | Gemma 2 9B | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |
Multilingual Gemma 2 9B leads
Gemma 2 9B: 36.6 (#238), Llama 13b: 16.6 (#297)
| Benchmark | Gemma 2 9B | Llama 13b |
|---|---|---|
| LMArena Non-English | 1188 | 819 |
| 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
Gemma 2 9B: 57.6 (#269), Llama 13b: 36.7 (#305)
| Benchmark | Gemma 2 9B | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1178 | 781 |
| LiveBench Instruction Following | 52.6% | — |
Long Context Not comparable
Gemma 2 9B: 36.3 (#233), Llama 13b: —
| Benchmark | Gemma 2 9B | Llama 13b |
|---|---|---|
| LMArena Longer Query | 1197 | — |
Writing & Preference Gemma 2 9B leads
Gemma 2 9B: 32.1 (#281), Llama 13b: 13.8 (#312)
| Benchmark | Gemma 2 9B | Llama 13b |
|---|---|---|
| LMArena Text | 1207 | 834 |
| LMArena Creative Writing | 1206 | 794 |
| LMArena Multi-Turn | 1193 | 753 |
| EQ-Bench Creative Writing | 841 | — |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Llama 13b?
Gemma 2 9B is the stronger model overall, scoring 25.9 to 24.4 on the Noometry Index.
Is Gemma 2 9B or Llama 13b better for coding?
Gemma 2 9B scores higher on coding benchmarks: 29.4 versus 21.4 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and Llama 13b share?
13 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Llama 13b has 21.