Model comparison
Gemma 3 12B vs Gemma 3n E4b IT
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 32.1 on the Noometry Index.
Last verified . 12 shared benchmarks.
GoogleSummary
- They share 12 benchmarks with published results for both. Gemma 3 12B scores higher in 3 categories and Gemma 3n E4b IT in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 3n E4b IT leads 35.1 to 22.3.
Side by side
| Gemma 3 12B | Gemma 3n E4b IT | |
|---|---|---|
| Provider | ||
| Noometry Index | 32.1 | 37.3 |
| Released | 2025-03-12 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 24 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3n E4b IT leads
Gemma 3 12B: 31.7 (#280), Gemma 3n E4b IT: 37.0 (#198)
| Benchmark | Gemma 3 12B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Coding | 1281 | 1268 |
| SciCode | 17.4% | — |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.5 (#108), Gemma 3n E4b IT: —
| Benchmark | Gemma 3 12B | Gemma 3n E4b IT |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning Gemma 3n E4b IT leads
Gemma 3 12B: 15.7 (#313), Gemma 3n E4b IT: 19.9 (#247)
| Benchmark | Gemma 3 12B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1284 |
| Kagi LLM Benchmark | — | 31.5% |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.5 | — |
Math Gemma 3n E4b IT leads
Gemma 3 12B: 22.3 (#279), Gemma 3n E4b IT: 35.1 (#188)
| Benchmark | Gemma 3 12B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Math | 1307 | 1251 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
Knowledge Gemma 3n E4b IT leads
Gemma 3 12B: 26.5 (#257), Gemma 3n E4b IT: 34.2 (#198)
| Benchmark | Gemma 3 12B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Expert | 1248 | 1246 |
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
Multimodal Not comparable
Gemma 3 12B: —, Gemma 3n E4b IT: —
| Benchmark | Gemma 3 12B | Gemma 3n E4b IT |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Gemma 3 12B leads
Gemma 3 12B: 45.7 (#165), Gemma 3n E4b IT: 43.4 (#183)
| Benchmark | Gemma 3 12B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Non-English | 1318 | 1285 |
| LMArena German | 1370 | 1311 |
| LMArena Russian | 1335 | 1288 |
| LMArena Chinese | — | 1309 |
| LMArena French | — | 1330 |
| LMArena Japanese | — | 1272 |
| LMArena Korean | — | 1259 |
| LMArena Spanish | — | 1305 |
Instruction Following Gemma 3 12B leads
Gemma 3 12B: 68.6 (#186), Gemma 3n E4b IT: 66.1 (#210)
| Benchmark | Gemma 3 12B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Instruction Following | 1299 | 1255 |
Long Context Gemma 3 12B leads
Gemma 3 12B: 40.0 (#162), Gemma 3n E4b IT: 38.7 (#191)
| Benchmark | Gemma 3 12B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Longer Query | 1317 | 1276 |
Writing & Preference Gemma 3n E4b IT leads
Gemma 3 12B: 47.5 (#209), Gemma 3n E4b IT: 50.1 (#186)
| Benchmark | Gemma 3 12B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Text | 1334 | 1306 |
| LMArena Creative Writing | 1331 | 1287 |
| LMArena Multi-Turn | 1334 | 1276 |
| EQ-Bench Creative Writing | 1126 | — |
Frequently asked questions
Is Gemma 3 12B better than Gemma 3n E4b IT?
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 32.1 on the Noometry Index.
Is Gemma 3 12B or Gemma 3n E4b IT better for coding?
Gemma 3n E4b IT scores higher on coding benchmarks: 37.0 versus 31.7 in the Noometry coding category.
How many benchmarks do Gemma 3 12B and Gemma 3n E4b IT share?
12 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Gemma 3n E4b IT has 18.