Model comparison
Gemma 3n E4b IT vs Llama 3.1-405B
Gemma 3n E4b IT is the stronger model overall, scoring 36.7 to 30.4 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 3.1-405B in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 3n E4b IT leads 32.5 to 17.3.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 31.5% for Gemma 3n E4b IT and 45% for Llama 3.1-405B.
Side by side
| Gemma 3n E4b IT | Llama 3.1-405B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 36.7 | 30.4 |
| Released | 2025-05-20 | 2024-07-23 |
| Weights | Open | Open |
| Context window | 33K | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.06 | — |
| Output $ / M tokens | $0.12 | — |
| Results tracked | 18 | 42 |
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: 36.4 (#193), Llama 3.1-405B: 32.7 (#257)
| Benchmark | Gemma 3n E4b IT | Llama 3.1-405B |
|---|---|---|
| LMArena Coding | 1269 | 1291 |
| WeirdML | — | 21.4% |
Agentic & Tool Use Not comparable
Gemma 3n E4b IT: —, Llama 3.1-405B: 20.9 (#131)
| Benchmark | Gemma 3n E4b IT | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
Reasoning Gemma 3n E4b IT leads
Gemma 3n E4b IT: 19.2 (#239), Llama 3.1-405B: 16.4 (#293)
| Benchmark | Gemma 3n E4b IT | Llama 3.1-405B |
|---|---|---|
| Kagi LLM Benchmark | 31.5% | 45% |
| LMArena Hard Prompts | 1284 | 1270 |
| SimpleBench | — | 23% |
| DTBench | — | 61.4% |
| BIG-Bench Hard | — | 82.9% |
| Epoch Capabilities Index | — | 128.76 |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math Gemma 3n E4b IT leads
Gemma 3n E4b IT: 32.5 (#186), Llama 3.1-405B: 17.3 (#283)
| Benchmark | Gemma 3n E4b IT | Llama 3.1-405B |
|---|---|---|
| LMArena Math | 1251 | 1281 |
| OTIS Mock AIME 2024-2025 | — | 9.7% |
| Omni-MATH | — | 24.9% |
| MATH Level 5 | — | 49.8% |
Knowledge Gemma 3n E4b IT leads
Gemma 3n E4b IT: 33.6 (#193), Llama 3.1-405B: 30.4 (#221)
| Benchmark | Gemma 3n E4b IT | Llama 3.1-405B |
|---|---|---|
| LMArena Expert | 1245 | 1243 |
| GPQA Diamond | — | 50.9% |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| GPQA (HELM) | — | 52.2% |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |
Multilingual Gemma 3n E4b IT leads
Gemma 3n E4b IT: 43.5 (#179), Llama 3.1-405B: 40.9 (#209)
| Benchmark | Gemma 3n E4b IT | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1285 | 1248 |
| LMArena Chinese | 1310 | 1242 |
| LMArena French | 1330 | 1278 |
| LMArena German | 1312 | 1252 |
| LMArena Japanese | 1274 | 1208 |
| LMArena Korean | 1259 | 1184 |
| LMArena Russian | 1288 | 1265 |
| LMArena Spanish | 1305 | 1259 |
Instruction Following Too close to call
Gemma 3n E4b IT: 66.3 (#205), Llama 3.1-405B: 66.1 (#209)
| Benchmark | Gemma 3n E4b IT | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1255 | 1259 |
| IFEval | — | 81.1% |
Long Context Too close to call
Gemma 3n E4b IT: 38.8 (#185), Llama 3.1-405B: 38.4 (#192)
| Benchmark | Gemma 3n E4b IT | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1277 | 1266 |
Writing & Preference Gemma 3n E4b IT leads
Gemma 3n E4b IT: 50.3 (#181), Llama 3.1-405B: 39.1 (#246)
| Benchmark | Gemma 3n E4b IT | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1306 | 1284 |
| LMArena Creative Writing | 1287 | 1262 |
| LMArena Multi-Turn | 1276 | 1297 |
| EQ-Bench Creative Writing | — | 870 |
| WildBench | — | 78.3% |
Frequently asked questions
Is Gemma 3n E4b IT better than Llama 3.1-405B?
Gemma 3n E4b IT is the stronger model overall, scoring 36.7 to 30.4 on the Noometry Index.
Is Gemma 3n E4b IT or Llama 3.1-405B better for coding?
Gemma 3n E4b IT scores higher on coding benchmarks: 36.4 versus 32.7 in the Noometry coding category.
How many benchmarks do Gemma 3n E4b IT and Llama 3.1-405B share?
18 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and Llama 3.1-405B has 42.