Granite 4.1 8B
IBM · 1 configuration
Intelligence6.6
Input / 1M$0.05
Output / 1M$0.10
Context131.1K
Tariff: CoreWeave · Source: models-dev · 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 default · Click a point to switch configuration
Granite 4.1 8B is a long-context instruct model capable of enhanced tool calling, instruction following, and chat capabilities.
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
6.6 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
43.3 %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.
3.4 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
27.8 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
38.6 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
12.3 %Specifications from the catalog
Inputtext
Outputtext
Tool callingYes
Structured outputYes
SpeedNot available
First tokenNot available
Maximum output131.1K
Catalog listing date2026-04-29