Model comparison
Gemma 2 9B vs Llama 2-7B
Llama 2-7B is the stronger model overall, scoring 29.1 to 25.9 on the Noometry Index.
Last verified . 20 shared benchmarks.
Google
MetaSummary
- They share 20 benchmarks with published results for both. Gemma 2 9B scores higher in 6 categories and Llama 2-7B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 2-7B leads 30.7 to 9.9.
Side by side
| Gemma 2 9B | Llama 2-7B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 25.9 | 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 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 2 9B: 29.4 (#304), Llama 2-7B: 29.2 (#307)
| Benchmark | Gemma 2 9B | Llama 2-7B |
|---|---|---|
| LMArena Coding | 1173 | 1002 |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
Reasoning Too close to call
Gemma 2 9B: 15.9 (#309), Llama 2-7B: 15.7 (#312)
| Benchmark | Gemma 2 9B | Llama 2-7B |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1009 |
| Epoch Capabilities Index | 119.83 | 99.06 |
| PIQA | 83.7% | 78.8% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 15.2% | — |
| LiveBench Data Analysis | 36.4% | — |
| BIG-Bench Hard | — | 39.2% |
| HellaSwag | — | 77.2% |
| LAMBADA | — | 73.3% |
| LiveBench | 28.7% | — |
| WinoGrande | — | 69.2% |
Math Llama 2-7B leads
Gemma 2 9B: 9.9 (#318), Llama 2-7B: 30.7 (#233)
| Benchmark | Gemma 2 9B | Llama 2-7B |
|---|---|---|
| LMArena Math | 1183 | 1042 |
| GSM8K | 84.9% | 16.7% |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
Knowledge Llama 2-7B leads
Gemma 2 9B: 9.7 (#305), Llama 2-7B: 28.2 (#248)
| Benchmark | Gemma 2 9B | Llama 2-7B |
|---|---|---|
| LMArena Expert | 1147 | 1036 |
| BoolQ | 85.7% | 77.9% |
| MMLU | 72.1% | 45.8% |
| GPQA Diamond | 27.5% | — |
| ARC (AI2) Challenge | — | 45.9% |
| OpenBookQA | — | 58.6% |
| TriviaQA | — | 73.7% |
Multimodal Not comparable
Gemma 2 9B: —, Llama 2-7B: —
| Benchmark | Gemma 2 9B | Llama 2-7B |
|---|---|---|
| ScienceQA | — | 43.1% |
Multilingual Gemma 2 9B leads
Gemma 2 9B: 36.6 (#238), Llama 2-7B: 23.8 (#293)
| Benchmark | Gemma 2 9B | Llama 2-7B |
|---|---|---|
| LMArena Non-English | 1188 | 973 |
| LMArena Chinese | 1185 | 973 |
| LMArena French | 1190 | 970 |
| LMArena German | 1186 | 978 |
| LMArena Russian | 1200 | 995 |
| LMArena Spanish | 1200 | 1007 |
| LMArena Japanese | 1144 | — |
| LMArena Korean | 1137 | — |
Instruction Following Gemma 2 9B leads
Gemma 2 9B: 57.6 (#269), Llama 2-7B: 50.8 (#298)
| Benchmark | Gemma 2 9B | Llama 2-7B |
|---|---|---|
| LMArena Instruction Following | 1178 | 1006 |
| LiveBench Instruction Following | 52.6% | — |
Long Context Gemma 2 9B leads
Gemma 2 9B: 36.3 (#233), Llama 2-7B: 30.4 (#287)
| Benchmark | Gemma 2 9B | Llama 2-7B |
|---|---|---|
| LMArena Longer Query | 1197 | 999 |
Writing & Preference Gemma 2 9B leads
Gemma 2 9B: 32.1 (#281), Llama 2-7B: 28.0 (#298)
| Benchmark | Gemma 2 9B | Llama 2-7B |
|---|---|---|
| LMArena Text | 1207 | 1053 |
| LMArena Creative Writing | 1206 | 1033 |
| LMArena Multi-Turn | 1193 | 1029 |
| EQ-Bench Creative Writing | 841 | — |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Llama 2-7B?
Llama 2-7B is the stronger model overall, scoring 29.1 to 25.9 on the Noometry Index.
Is Gemma 2 9B or Llama 2-7B better for coding?
They score almost the same on coding (29.4 vs 29.2); test both on your own repository before choosing.
How many benchmarks do Gemma 2 9B and Llama 2-7B share?
20 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Llama 2-7B has 29.