Model comparison
Gemma 3n E4b IT vs Llama 2-13B
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 29.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
MetaSummary
- They share 17 benchmarks with published results for both. Gemma 3n E4b IT scores higher in 8 categories and Llama 2-13B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3n E4b IT leads 50.1 to 29.8.
Side by side
| Gemma 3n E4b IT | Llama 2-13B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 37.3 | 29.6 |
| Released | — | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3n E4b IT leads
Gemma 3n E4b IT: 37.0 (#198), Llama 2-13B: 30.9 (#291)
| Benchmark | Gemma 3n E4b IT | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1268 | 1062 |
Reasoning Gemma 3n E4b IT leads
Gemma 3n E4b IT: 19.9 (#247), Llama 2-13B: 12.8 (#337)
| Benchmark | Gemma 3n E4b IT | Llama 2-13B |
|---|---|---|
| LMArena Hard Prompts | 1284 | 1051 |
| Kagi LLM Benchmark | 31.5% | — |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.2% |
| BIG-Bench Hard | — | 58.2% |
| Epoch Capabilities Index | — | 106.17 |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math Gemma 3n E4b IT leads
Gemma 3n E4b IT: 35.1 (#188), Llama 2-13B: 31.1 (#229)
| Benchmark | Gemma 3n E4b IT | Llama 2-13B |
|---|---|---|
| LMArena Math | 1251 | 1065 |
| GSM8K | — | 36.9% |
Knowledge Gemma 3n E4b IT leads
Gemma 3n E4b IT: 34.2 (#198), Llama 2-13B: 28.1 (#249)
| Benchmark | Gemma 3n E4b IT | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1246 | 1030 |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
Gemma 3n E4b IT: —, Llama 2-13B: —
| Benchmark | Gemma 3n E4b IT | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |
Multilingual Gemma 3n E4b IT leads
Gemma 3n E4b IT: 43.4 (#183), Llama 2-13B: 26.5 (#279)
| Benchmark | Gemma 3n E4b IT | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1285 | 1024 |
| LMArena Chinese | 1309 | 1001 |
| LMArena French | 1330 | 1044 |
| LMArena German | 1311 | 1009 |
| LMArena Japanese | 1272 | 894 |
| LMArena Korean | 1259 | 953 |
| LMArena Russian | 1288 | 1055 |
| LMArena Spanish | 1305 | 1087 |
Instruction Following Gemma 3n E4b IT leads
Gemma 3n E4b IT: 66.1 (#210), Llama 2-13B: 53.3 (#287)
| Benchmark | Gemma 3n E4b IT | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1255 | 1045 |
Long Context Gemma 3n E4b IT leads
Gemma 3n E4b IT: 38.7 (#191), Llama 2-13B: 32.3 (#269)
| Benchmark | Gemma 3n E4b IT | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1276 | 1064 |
Writing & Preference Gemma 3n E4b IT leads
Gemma 3n E4b IT: 50.1 (#186), Llama 2-13B: 29.8 (#289)
| Benchmark | Gemma 3n E4b IT | Llama 2-13B |
|---|---|---|
| LMArena Text | 1306 | 1084 |
| LMArena Creative Writing | 1287 | 1047 |
| LMArena Multi-Turn | 1276 | 1050 |
Frequently asked questions
Is Gemma 3n E4b IT better than Llama 2-13B?
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 29.6 on the Noometry Index.
Is Gemma 3n E4b IT or Llama 2-13B better for coding?
Gemma 3n E4b IT scores higher on coding benchmarks: 37.0 versus 30.9 in the Noometry coding category.
How many benchmarks do Gemma 3n E4b IT and Llama 2-13B share?
17 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and Llama 2-13B has 32.