Model comparison
Gemma 1.1 2b IT vs Llama 13b
Gemma 1.1 2b IT is the stronger model overall, scoring 29.3 to 24.4 on the Noometry Index.
Last verified . 8 shared benchmarks.
Google
MetaSummary
- They share 8 benchmarks with published results for both. Gemma 1.1 2b IT scores higher in 6 categories and Llama 13b in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Gemma 1.1 2b IT leads 49.9 to 36.7.
Side by side
| Gemma 1.1 2b IT | Llama 13b | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 29.3 | 24.4 |
| Released | — | 2023-02-24 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 16 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 1.1 2b IT leads
Gemma 1.1 2b IT: 30.1 (#299), Llama 13b: 21.4 (#337)
| Benchmark | Gemma 1.1 2b IT | Llama 13b |
|---|---|---|
| LMArena Coding | 1034 | 683 |
| HumanEval+ | 17.7% | — |
| MBPP+ | 23.3% | — |
Reasoning Gemma 1.1 2b IT leads
Gemma 1.1 2b IT: 19.1 (#270), Llama 13b: 14.0 (#329)
| Benchmark | Gemma 1.1 2b IT | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1005 | 728 |
| BIG-Bench Hard | — | 37.9% |
| Epoch Capabilities Index | — | 100.58 |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |
Math Gemma 1.1 2b IT leads
Gemma 1.1 2b IT: 30.8 (#232), Llama 13b: 26.7 (#256)
| Benchmark | Gemma 1.1 2b IT | Llama 13b |
|---|---|---|
| LMArena Math | 1047 | 838 |
| GSM8K | — | 20.6% |
Knowledge Not comparable
Gemma 1.1 2b IT: 26.5 (#258), Llama 13b: —
| Benchmark | Gemma 1.1 2b IT | Llama 13b |
|---|---|---|
| LMArena Expert | 970 | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
Gemma 1.1 2b IT: —, Llama 13b: —
| Benchmark | Gemma 1.1 2b IT | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |
Multilingual Gemma 1.1 2b IT leads
Gemma 1.1 2b IT: 24.6 (#289), Llama 13b: 16.6 (#297)
| Benchmark | Gemma 1.1 2b IT | Llama 13b |
|---|---|---|
| LMArena Non-English | 988 | 819 |
| LMArena Chinese | 1012 | — |
| LMArena German | 944 | — |
| LMArena Korean | 899 | — |
| LMArena Russian | 990 | — |
Instruction Following Gemma 1.1 2b IT leads
Gemma 1.1 2b IT: 49.9 (#299), Llama 13b: 36.7 (#305)
| Benchmark | Gemma 1.1 2b IT | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 992 | 781 |
Long Context Not comparable
Gemma 1.1 2b IT: 30.6 (#286), Llama 13b: —
| Benchmark | Gemma 1.1 2b IT | Llama 13b |
|---|---|---|
| LMArena Longer Query | 1003 | — |
Writing & Preference Gemma 1.1 2b IT leads
Gemma 1.1 2b IT: 25.1 (#306), Llama 13b: 13.8 (#312)
| Benchmark | Gemma 1.1 2b IT | Llama 13b |
|---|---|---|
| LMArena Text | 1022 | 834 |
| LMArena Creative Writing | 998 | 794 |
| LMArena Multi-Turn | 959 | 753 |
Frequently asked questions
Is Gemma 1.1 2b IT better than Llama 13b?
Gemma 1.1 2b IT is the stronger model overall, scoring 29.3 to 24.4 on the Noometry Index.
Is Gemma 1.1 2b IT or Llama 13b better for coding?
Gemma 1.1 2b IT scores higher on coding benchmarks: 30.1 versus 21.4 in the Noometry coding category.
How many benchmarks do Gemma 1.1 2b IT and Llama 13b share?
8 benchmarks have published results for both models. Gemma 1.1 2b IT has 16 scored results on Noometry and Llama 13b has 21.