Gemma 4 E4B
Google · 2 thinking configurations
Intelligence8.9
Input / 1M$0.02
Output / 1M$0.10
Context128K
Tariff: Google · Source: artificial-analysis · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
Scroll the chart ↔ · tap a point for details
Efficient frontier: best measured score at each cost2 measured configurations · 0 without both values
Selected: thinking thinking · Click a point to switch configuration
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
8.9 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
57.6 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
3.8 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
1.9 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
20.8 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
44.2 %MMMU-ProMultimodal understanding of academic problems that include images.
51.4 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
8.6 %Specifications from the catalog
Inputtext
Outputtext
Tool callingNot available
Structured outputNot available
Speed63.2 tok/s
First token0.84 s
Maximum output—
Catalog listing dateNot available