TAU2
Measured May 14, 2026Source
Score
0.05
ModelsGoogle
15 0 
Gemma 3n E4B Instruct
GoogleGoogleUnited States
Gemma 3n E4B Instruct is a lightweight, efficient instruction-tuned model from Google's Gemma family, optimized for on-device and edge deployment. It delivers strong reasoning and instruction-following capabilities within a compact 4B parameter footprint, making it suitable for fast and cost-effective local inference.
ReasoningFastCheap
Input / 1M tokens
$0.02Output / 1M tokens
$0.04Output tokens/s
36.13First-token seconds
0.78sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.02
Lcr
Measured May 14, 2026Source
Score
0
Ifbench
Measured May 14, 2026Source
Score
0.28
Aime 25
Measured May 14, 2026Source
Score
0.14
Aime
Measured May 14, 2026Source
Score
0.14
Math 500
Measured May 14, 2026Source
Score
0.77
Scicode
Measured May 14, 2026Source
Score
0.08
Livecodebench
Measured May 14, 2026Source
Score
0.15
Hle
Measured May 14, 2026Source
Score
0.04
Gpqa
Measured May 14, 2026Source
Score
0.3
Mmlu Pro
Measured May 14, 2026Source
Score
0.49
Artificial Analysis Math Index
Measured May 14, 2026Source
Score
14.3
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
4.2
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
6.4
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
Discussion
Thinking... Make sure you are connected to GitHub server