Model comparison
Gemma 2 9B vs Llama 2-13B
Llama 2-13B is the stronger model overall, scoring 29.1 to 25.7 on the Noometry Index.
Last verified . 22 shared benchmarks.
Google
MetaSummary
- They share 22 benchmarks with published results for both. Gemma 2 9B scores higher in 5 categories and Llama 2-13B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 2-13B leads 28.7 to 9.3.
Side by side
| Gemma 2 9B | Llama 2-13B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 25.7 | 29.1 |
| Released | 2024-06-24 | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-13B leads
Gemma 2 9B: 29.0 (#299), Llama 2-13B: 30.4 (#287)
| Benchmark | Gemma 2 9B | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1174 | 1062 |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
Reasoning Gemma 2 9B leads
Gemma 2 9B: 15.3 (#306), Llama 2-13B: 12.3 (#333)
| Benchmark | Gemma 2 9B | Llama 2-13B |
|---|---|---|
| LMArena Hard Prompts | 1172 | 1051 |
| Epoch Capabilities Index | 119.78 | 105.8 |
| PIQA | 83.7% | 80.8% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 15.2% | — |
| DTBench | — | 42.2% |
| LiveBench Data Analysis | 36.4% | — |
| BIG-Bench Hard | — | 58.2% |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| LiveBench | 28.7% | — |
| WinoGrande | — | 72.8% |
Math Llama 2-13B leads
Gemma 2 9B: 9.3 (#312), Llama 2-13B: 28.7 (#226)
| Benchmark | Gemma 2 9B | Llama 2-13B |
|---|---|---|
| LMArena Math | 1183 | 1065 |
| GSM8K | 84.9% | 36.9% |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
Knowledge Llama 2-13B leads
Gemma 2 9B: 9.7 (#300), Llama 2-13B: 27.5 (#244)
| Benchmark | Gemma 2 9B | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1147 | 1030 |
| BoolQ | 85.7% | 82.4% |
| MMLU | 72.1% | 55.6% |
| GPQA Diamond | 27.5% | — |
| ARC (AI2) Challenge | — | 60.3% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
Gemma 2 9B: —, Llama 2-13B: —
| Benchmark | Gemma 2 9B | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |
Multilingual Gemma 2 9B leads
Gemma 2 9B: 36.8 (#233), Llama 2-13B: 26.7 (#274)
| Benchmark | Gemma 2 9B | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1188 | 1024 |
| LMArena Chinese | 1185 | 1001 |
| LMArena French | 1189 | 1043 |
| LMArena German | 1186 | 1009 |
| LMArena Japanese | 1144 | 894 |
| LMArena Korean | 1137 | 953 |
| LMArena Russian | 1200 | 1055 |
| LMArena Spanish | 1200 | 1086 |
Instruction Following Gemma 2 9B leads
Gemma 2 9B: 57.8 (#264), Llama 2-13B: 53.5 (#282)
| Benchmark | Gemma 2 9B | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1178 | 1046 |
| LiveBench Instruction Following | 52.6% | — |
Long Context Gemma 2 9B leads
Gemma 2 9B: 36.3 (#228), Llama 2-13B: 32.3 (#264)
| Benchmark | Gemma 2 9B | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1197 | 1064 |
Writing & Preference Gemma 2 9B leads
Gemma 2 9B: 32.3 (#276), Llama 2-13B: 30.0 (#284)
| Benchmark | Gemma 2 9B | Llama 2-13B |
|---|---|---|
| LMArena Text | 1207 | 1085 |
| LMArena Creative Writing | 1206 | 1047 |
| LMArena Multi-Turn | 1193 | 1050 |
| EQ-Bench Creative Writing | 841 | — |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Llama 2-13B?
Llama 2-13B is the stronger model overall, scoring 29.1 to 25.7 on the Noometry Index.
Is Gemma 2 9B or Llama 2-13B better for coding?
Llama 2-13B scores higher on coding benchmarks: 30.4 versus 29.0 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and Llama 2-13B share?
22 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Llama 2-13B has 32.