Model comparison
Gemma 3 4B vs Gemma 3n E4b IT
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 28.1 on the Noometry Index.
Last verified . 13 shared benchmarks.
GoogleSummary
- They share 13 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and Gemma 3n E4b IT in 8 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 3n E4b IT leads 34.2 to 11.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 25.2% for Gemma 3 4B and 31.5% for Gemma 3n E4b IT.
Side by side
| Gemma 3 4B | Gemma 3n E4b IT | |
|---|---|---|
| Provider | ||
| Noometry Index | 28.1 | 37.3 |
| Released | 2025-03-12 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 22 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3n E4b IT leads
Gemma 3 4B: 35.9 (#215), Gemma 3n E4b IT: 37.0 (#198)
| Benchmark | Gemma 3 4B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Coding | 1230 | 1268 |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), Gemma 3n E4b IT: —
| Benchmark | Gemma 3 4B | Gemma 3n E4b IT |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Gemma 3n E4b IT leads
Gemma 3 4B: 13.2 (#335), Gemma 3n E4b IT: 19.9 (#247)
| Benchmark | Gemma 3 4B | Gemma 3n E4b IT |
|---|---|---|
| Kagi LLM Benchmark | 25.2% | 31.5% |
| LMArena Hard Prompts | 1253 | 1284 |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |
Math Gemma 3n E4b IT leads
Gemma 3 4B: 16.8 (#292), Gemma 3n E4b IT: 35.1 (#188)
| Benchmark | Gemma 3 4B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Math | 1239 | 1251 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |
Knowledge Gemma 3n E4b IT leads
Gemma 3 4B: 11.8 (#299), Gemma 3n E4b IT: 34.2 (#198)
| Benchmark | Gemma 3 4B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Expert | 1223 | 1246 |
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |
Multilingual Too close to call
Gemma 3 4B: 42.5 (#194), Gemma 3n E4b IT: 43.4 (#183)
| Benchmark | Gemma 3 4B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Non-English | 1273 | 1285 |
| LMArena German | 1281 | 1311 |
| LMArena Russian | 1294 | 1288 |
| LMArena Chinese | — | 1309 |
| LMArena French | — | 1330 |
| LMArena Japanese | — | 1272 |
| LMArena Korean | — | 1259 |
| LMArena Spanish | — | 1305 |
Instruction Following Too close to call
Gemma 3 4B: 65.2 (#225), Gemma 3n E4b IT: 66.1 (#210)
| Benchmark | Gemma 3 4B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Instruction Following | 1239 | 1255 |
Long Context Too close to call
Gemma 3 4B: 38.7 (#194), Gemma 3n E4b IT: 38.7 (#191)
| Benchmark | Gemma 3 4B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Longer Query | 1273 | 1276 |
Writing & Preference Gemma 3n E4b IT leads
Gemma 3 4B: 42.0 (#239), Gemma 3n E4b IT: 50.1 (#186)
| Benchmark | Gemma 3 4B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Text | 1291 | 1306 |
| LMArena Creative Writing | 1271 | 1287 |
| LMArena Multi-Turn | 1255 | 1276 |
| EQ-Bench Creative Writing | 1068 | — |
Frequently asked questions
Is Gemma 3 4B better than Gemma 3n E4b IT?
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 28.1 on the Noometry Index.
Is Gemma 3 4B or Gemma 3n E4b IT better for coding?
Gemma 3n E4b IT scores higher on coding benchmarks: 37.0 versus 35.9 in the Noometry coding category.
How many benchmarks do Gemma 3 4B and Gemma 3n E4b IT share?
13 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Gemma 3n E4b IT has 18.