Granite 4.2 3B
IBM · 1 configuration
Intelligence9.1
Input / 1M$0.03
Output / 1M$0.12
Context131.1K
Tariff: IBM · 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 cost1 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.
9.1 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
55.9 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
6.6 %SciCodeCode generation for scientific research problems.
25.3 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
13.9 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
9.2 %Specifications from the catalog
Inputtext
Outputtext
Tool callingNot available
Structured outputNot available
Speed223.8 tok/s
First token0.51 s
Maximum output—
Catalog listing dateNot available