Model comparison
Gemma 3n E4b IT vs Llama 3-70B
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 28.8 on the Noometry Index.
Last verified . 18 shared benchmarks.
Google
MetaSummary
- They share 18 benchmarks with published results for both. Gemma 3n E4b IT scores higher in 8 categories and Llama 3-70B 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 12.8.
Side by side
| Gemma 3n E4b IT | Llama 3-70B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 37.3 | 28.8 |
| Released | — | 2024-04-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 31 |
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 3-70B: 35.8 (#218)
| Benchmark | Gemma 3n E4b IT | Llama 3-70B |
|---|---|---|
| LMArena Coding | 1268 | 1206 |
| BigCodeBench Instruct | — | 43.6% |
| BigCodeBench Complete | — | 54.5% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Not comparable
Gemma 3n E4b IT: —, Llama 3-70B: 21.1 (#139)
| Benchmark | Gemma 3n E4b IT | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning Gemma 3n E4b IT leads
Gemma 3n E4b IT: 19.9 (#247), Llama 3-70B: 18.0 (#288)
| Benchmark | Gemma 3n E4b IT | Llama 3-70B |
|---|---|---|
| Kagi LLM Benchmark | 31.5% | 35.1% |
| LMArena Hard Prompts | 1284 | 1195 |
| DTBench | — | 54.2% |
| Epoch Capabilities Index | — | 122.93 |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |
Math Gemma 3n E4b IT leads
Gemma 3n E4b IT: 35.1 (#188), Llama 3-70B: 12.8 (#305)
| Benchmark | Gemma 3n E4b IT | Llama 3-70B |
|---|---|---|
| LMArena Math | 1251 | 1218 |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| MATH Level 5 | — | 22.6% |
Knowledge Gemma 3n E4b IT leads
Gemma 3n E4b IT: 34.2 (#198), Llama 3-70B: 20.8 (#277)
| Benchmark | Gemma 3n E4b IT | Llama 3-70B |
|---|---|---|
| LMArena Expert | 1246 | 1149 |
| GPQA Diamond | — | 40.6% |
| MMLU | — | 79.3% |
Multilingual Gemma 3n E4b IT leads
Gemma 3n E4b IT: 43.4 (#183), Llama 3-70B: 33.6 (#251)
| Benchmark | Gemma 3n E4b IT | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1285 | 1142 |
| LMArena Chinese | 1309 | 1114 |
| LMArena French | 1330 | 1232 |
| LMArena German | 1311 | 1169 |
| LMArena Japanese | 1272 | 1017 |
| LMArena Korean | 1259 | 1017 |
| LMArena Russian | 1288 | 1159 |
| LMArena Spanish | 1305 | 1241 |
Instruction Following Gemma 3n E4b IT leads
Gemma 3n E4b IT: 66.1 (#210), Llama 3-70B: 62.5 (#238)
| Benchmark | Gemma 3n E4b IT | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1255 | 1194 |
Long Context Gemma 3n E4b IT leads
Gemma 3n E4b IT: 38.7 (#191), Llama 3-70B: 35.6 (#240)
| Benchmark | Gemma 3n E4b IT | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1276 | 1174 |
Writing & Preference Gemma 3n E4b IT leads
Gemma 3n E4b IT: 50.1 (#186), Llama 3-70B: 42.8 (#231)
| Benchmark | Gemma 3n E4b IT | Llama 3-70B |
|---|---|---|
| LMArena Text | 1306 | 1221 |
| LMArena Creative Writing | 1287 | 1210 |
| LMArena Multi-Turn | 1276 | 1223 |
Frequently asked questions
Is Gemma 3n E4b IT better than Llama 3-70B?
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 28.8 on the Noometry Index.
Is Gemma 3n E4b IT or Llama 3-70B better for coding?
Gemma 3n E4b IT scores higher on coding benchmarks: 37.0 versus 35.8 in the Noometry coding category.
How many benchmarks do Gemma 3n E4b IT and Llama 3-70B share?
18 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and Llama 3-70B has 31.