Aime
Measured May 29, 2026Source
Score
0.11
Models15 0 
Gemma 3n E4B Instruct Preview (May '25)
GoogleGoogleUnited States
Gemma 3n E4B Instruct Preview is a 4-billion parameter, instruction-tuned model from Google's Gemma family, optimized for efficient on-device and edge deployment. This preview version focuses on strong instruction following and reasoning capabilities within a compact size.
FastCheapReasoning
Input / 1M tokens
$0.00Output / 1M tokens
$0.00Supported plans
0Benchmark history
Evaluations
Math 500
Measured May 29, 2026Source
Score
0.75
Scicode
Measured May 29, 2026Source
Score
0.09
Livecodebench
Measured May 29, 2026Source
Score
0.14
Hle
Measured May 29, 2026Source
Score
0.05
Gpqa
Measured May 29, 2026Source
Score
0.28
Mmlu Pro
Measured May 29, 2026Source
Score
0.48
Artificial Analysis Intelligence Index
Measured May 29, 2026Source
Score
10.1
TAU2
Measured May 29, 2026Source
Score
0.05
Terminalbench Hard
Measured May 29, 2026Source
Score
0.02
Lcr
Measured May 29, 2026Source
Score
0
Ifbench
Measured May 29, 2026Source
Score
0.28
Aime 25
Measured May 29, 2026Source
Score
0.14
Artificial Analysis Math Index
Measured May 29, 2026Source
Score
14.3
Artificial Analysis Coding Index
Measured May 29, 2026Source
Score
4.2
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
User ratings
Loading ratings...
Discussion
Thinking... Make sure you are connected to GitHub server