Granite 4.1 3B

Granite 4.1 3B

IBM · Released Apr 29, 2026 Emerging New
Intelligence #498 / 556
10.9 Our Score
AA Index #327 / 365
8.5 Artificial Analysis
Input
Not priced
Output
Not priced
Context
Not reported

Analysis Summary

Granite 4.1 3B sits in the Emerging tier on our leaderboard, ranked #498 of 556 published models on overall intelligence. At $0.000 input and $0.000 output per 1M tokens, it is among the most expensive on the market.

Editorial notes

Granite 4.1 3B is a small IBM model with very low benchmark scores across all dimensions; best suited to narrow on-device tasks where model size is the primary constraint.

Assessed May 14, 2026

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence1.6Technical1Value0Content2
Intelligence 1.6/10
Technical 1/10
Content 2/10
Value 0/10

Performance Indices

Source: Artificial Analysis

8.5 Intelligence Index
5.5 Coding Index
10.9 Agentic Index

Benchmark Scores

Intelligence

GPQA Diamond 31.4% Graduate-level scientific reasoning
HLE 3.4% Humanity's Last Exam
SciCode 11.9% Scientific computing

Technical

TerminalBench Hard 2.3% Agentic terminal tasks
τ²-Bench 19.6% Conversational agent benchmark

Content

IFBench 33.7% Instruction following
LCR 3% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does Granite 4.1 3B stack up?

Compare side-by-side with other emerging models.

Compare Models

Model Information

ProviderIBM
Release Date April 29, 2026
Status Active