Model comparison
Gemma 2B vs Llama 2-13B
Gemma 2B and Llama 2-13B score almost the same on the Noometry Index (29.6 vs 29.6), so choose on price, context window or the category you care about most.
Last verified . 21 shared benchmarks.
Google
MetaSummary
- They share 21 benchmarks with published results for both. Gemma 2B scores higher in 1 category and Llama 2-13B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemma 2B leads 18.8 to 12.8.
Side by side
| Gemma 2B | Llama 2-13B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 29.6 | 29.6 |
| Released | 2024-02-21 | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 23 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-13B leads
Gemma 2B: 29.4 (#305), Llama 2-13B: 30.9 (#291)
| Benchmark | Gemma 2B | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1010 | 1062 |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Reasoning Gemma 2B leads
Gemma 2B: 18.8 (#275), Llama 2-13B: 12.8 (#337)
| Benchmark | Gemma 2B | Llama 2-13B |
|---|---|---|
| LMArena Hard Prompts | 989 | 1051 |
| BIG-Bench Hard | 35.2% | 58.2% |
| Epoch Capabilities Index | 94.2 | 106.17 |
| HellaSwag | 71.4% | 80.7% |
| PIQA | 77.3% | 80.8% |
| WinoGrande | 65.4% | 72.8% |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.2% |
| LAMBADA | — | 76.5% |
Math Llama 2-13B leads
Gemma 2B: 30.0 (#239), Llama 2-13B: 31.1 (#229)
| Benchmark | Gemma 2B | Llama 2-13B |
|---|---|---|
| LMArena Math | 1009 | 1065 |
| GSM8K | 17.7% | 36.9% |
Knowledge Not comparable
Gemma 2B: —, Llama 2-13B: 28.1 (#249)
| Benchmark | Gemma 2B | Llama 2-13B |
|---|---|---|
| ARC (AI2) Challenge | 42.1% | 60.3% |
| BoolQ | 69.4% | 82.4% |
| MMLU | 42.3% | 55.6% |
| TriviaQA | 53.2% | 79.6% |
| LMArena Expert | — | 1030 |
| OpenBookQA | — | 57% |
Multimodal Not comparable
Gemma 2B: —, Llama 2-13B: —
| Benchmark | Gemma 2B | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |
Multilingual Llama 2-13B leads
Gemma 2B: 23.0 (#294), Llama 2-13B: 26.5 (#279)
| Benchmark | Gemma 2B | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 958 | 1024 |
| LMArena Chinese | 986 | 1001 |
| LMArena Russian | 937 | 1055 |
| LMArena French | — | 1044 |
| LMArena German | — | 1009 |
| LMArena Japanese | — | 894 |
| LMArena Korean | — | 953 |
| LMArena Spanish | — | 1087 |
Instruction Following Llama 2-13B leads
Gemma 2B: 48.5 (#302), Llama 2-13B: 53.3 (#287)
| Benchmark | Gemma 2B | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 970 | 1045 |
Long Context Llama 2-13B leads
Gemma 2B: 29.9 (#291), Llama 2-13B: 32.3 (#269)
| Benchmark | Gemma 2B | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 981 | 1064 |
Writing & Preference Llama 2-13B leads
Gemma 2B: 24.0 (#308), Llama 2-13B: 29.8 (#289)
| Benchmark | Gemma 2B | Llama 2-13B |
|---|---|---|
| LMArena Text | 1002 | 1084 |
| LMArena Creative Writing | 987 | 1047 |
| LMArena Multi-Turn | 945 | 1050 |
Frequently asked questions
Is Gemma 2B better than Llama 2-13B?
Gemma 2B and Llama 2-13B score almost the same on the Noometry Index (29.6 vs 29.6), so choose on price, context window or the category you care about most.
Is Gemma 2B or Llama 2-13B better for coding?
Llama 2-13B scores higher on coding benchmarks: 30.9 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2B and Llama 2-13B share?
21 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Llama 2-13B has 32.