Model comparison
Gemma 3n E4b IT vs Llama 2-70B
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 24.4 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 2-70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 3n E4b IT leads 35.1 to 8.1.
Side by side
| Gemma 3n E4b IT | Llama 2-70B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 37.3 | 24.4 |
| Released | — | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 35 |
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 2-70B: 31.4 (#286)
| Benchmark | Gemma 3n E4b IT | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1268 | 1079 |
Reasoning Gemma 3n E4b IT leads
Gemma 3n E4b IT: 19.9 (#247), Llama 2-70B: 14.4 (#325)
| Benchmark | Gemma 3n E4b IT | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1284 | 1073 |
| Kagi LLM Benchmark | 31.5% | — |
| DTBench | — | 41.6% |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| Epoch Capabilities Index | — | 113.79 |
| ForecastBench | — | 51.4 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |
Math Gemma 3n E4b IT leads
Gemma 3n E4b IT: 35.1 (#188), Llama 2-70B: 8.1 (#326)
| Benchmark | Gemma 3n E4b IT | Llama 2-70B |
|---|---|---|
| LMArena Math | 1251 | 1091 |
| OTIS Mock AIME 2024-2025 | — | 0% |
| MATH Level 5 | — | 3.3% |
| GSM8K | — | 69.6% |
Knowledge Gemma 3n E4b IT leads
Gemma 3n E4b IT: 34.2 (#198), Llama 2-70B: 7.4 (#310)
| Benchmark | Gemma 3n E4b IT | Llama 2-70B |
|---|---|---|
| LMArena Expert | 1246 | 1039 |
| GPQA Diamond | — | 26.3% |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |
Multilingual Gemma 3n E4b IT leads
Gemma 3n E4b IT: 43.4 (#183), Llama 2-70B: 27.7 (#274)
| Benchmark | Gemma 3n E4b IT | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1285 | 1045 |
| LMArena Chinese | 1309 | 995 |
| LMArena French | 1330 | 1090 |
| LMArena German | 1311 | 1041 |
| LMArena Japanese | 1272 | 927 |
| LMArena Korean | 1259 | 964 |
| LMArena Russian | 1288 | 1083 |
| LMArena Spanish | 1305 | 1143 |
Instruction Following Gemma 3n E4b IT leads
Gemma 3n E4b IT: 66.1 (#210), Llama 2-70B: 54.9 (#278)
| Benchmark | Gemma 3n E4b IT | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1255 | 1071 |
Long Context Gemma 3n E4b IT leads
Gemma 3n E4b IT: 38.7 (#191), Llama 2-70B: 32.3 (#270)
| Benchmark | Gemma 3n E4b IT | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1276 | 1062 |
Writing & Preference Gemma 3n E4b IT leads
Gemma 3n E4b IT: 50.1 (#186), Llama 2-70B: 32.3 (#279)
| Benchmark | Gemma 3n E4b IT | Llama 2-70B |
|---|---|---|
| LMArena Text | 1306 | 1115 |
| LMArena Creative Writing | 1287 | 1075 |
| LMArena Multi-Turn | 1276 | 1088 |
Frequently asked questions
Is Gemma 3n E4b IT better than Llama 2-70B?
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 24.4 on the Noometry Index.
Is Gemma 3n E4b IT or Llama 2-70B better for coding?
Gemma 3n E4b IT scores higher on coding benchmarks: 37.0 versus 31.4 in the Noometry coding category.
How many benchmarks do Gemma 3n E4b IT and Llama 2-70B share?
17 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and Llama 2-70B has 35.