Google · model passport

Gemma 3n E4b It

gemma-3n-e4b-it

Open weights
Gemma licence
Released 2025-06-26(curated)

Overall · LMArena: 1,318#246 of 396
Best percentile: 38.1Overall
Cohort standing: 40.5median 51.6

What the data says

Benchmarked on 4 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 10.7 percentile points between its best and worst axis — 38.1 pct on Overall versus 27.4 pct on Coding.

Overall38.1 pct1,318Verify →
Hard prompts34.6 pct1,312Verify →
Instruction following33.3 pct1,282Verify →
Coding27.4 pct1,307Verify →
WebDev ArenaNot benchmarked
Vision ArenaNot benchmarked
Factuality ArenaNot benchmarked
Search ArenaNot benchmarked
Document ArenaNot benchmarked
Agent ArenaNot benchmarked
GPQA DiamondNot benchmarked
AIME (math)Not benchmarked
FrontierMathNot benchmarked
SimpleQA VerifiedNot benchmarked
ARC-AGI-2Not benchmarked
Humanity's Last ExamNot benchmarked
SimpleBenchNot benchmarked
LiveBenchNot benchmarked
BFCL v4 (function calling)Not benchmarked
SWE-bench Verified (live board)Not benchmarked
Terminal-Bench 4.0Not benchmarked
MMLU-Pro (Artificial Analysis)Not benchmarked
LiveCodeBench (Artificial Analysis)Not benchmarked
IFBench (Artificial Analysis)Not benchmarked
HHEM Hallucination (Vectara)Not benchmarked
SWE-bench VerifiedNot benchmarked
Terminal-BenchNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

gemma-3n-e4b-it stands at 40.5 (raw mean 33.4) — measured on 4 of 27 axes.
standingtemplateVerify →
gemma-3n-e4b-it stands at 40.5 versus a cohort median of 51.6 across 146 models released within 180 days — below the peer median.
cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →