Granite 4.1 3B

Granite 4.1 3B

IBM · Released Apr 29, 2026
Intelligence #690 / 756
10.8 our score
AA Index #355 / 435
1.0 Artificial Analysis
Input Price
Not priced
Output Price
Not priced
Context
Not reported

Analysis Summary

Granite 4.1 3B is a small text model with measured results for reasoning, coding, instruction following, long-context work, and tool-oriented tasks. Its compact scale may suit lightweight infrastructure and narrowly scoped automation, although pricing and context capacity are not provided.

Performance is limited across the supplied capability measures, especially long-context reasoning, coding, and agentic interaction. It can be considered for simple classification, routing, extraction, or preprocessing where mistakes are easy to detect and correct. It is not an appropriate primary model for client-facing copy, complex SEO planning, software engineering, or autonomous tool use. Adopt only when low resource requirements are the main constraint and the task has strong guardrails.

Assessed September 7, 2026

Editorial notes

Granite 4.1 3B is a compact measured model for constrained tasks, but very low reasoning, coding, long-context, and agentic results make it unsuitable for demanding client workflows.

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

DFO Verdict

Granite 4.1 3B is a compact measured model for constrained tasks, but very low reasoning, coding, long-context, and agentic results make it unsuitable for demanding client workflows.

#690 of 756 overall Down 33 this week

Benchmark scores

GPQA Diamond 31.4%
HLE 3.4%
SciCode 11.9%
TerminalBench Hard 2.3%
τ²-Bench 19.6%
IFBench 33.7%
LCR 3%

Magenta = intelligence · Ink = technical/agentic · Cyan = content & long-context · Grey = community benchmarks. Data: Artificial Analysis, Hugging Face.

1 Intelligence Index·4.7 Coding Index·0.4 Agentic Index

How Granite 4.1 3B compares

Granite 4.1 3B ranks #355 of 435 AI models we track for overall intelligence, #199 of 208 for coding, #186 of 190 for agentic tasks. Granite 4.1 3B is currently free to use via OpenRouter.

Position in the field
Intelligence: smarter than 9% of models #690
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
Granite 4.1 3B $0.00 in $0.00 out
OpenAI: GPT-6 Astra $10.00 in $50.00 out
Anthropic: Claude Fable 5.1 $10.00 in $50.00 out
Claude Opus 5 $5.00 in $25.00 out

Dark bar = input · light bar = output, scaled to the priciest peer.

Context window vs peers · tokens

1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.

Intelligence0.7Technical0.3Value0Content3.1
Performance profile

Strongest on business fit. The pulled-in value corner is the trade-off, and if the shape matters more than the price, this is your model.

Compare shapes side-by-side →

Frequently asked questions about Granite 4.1 3B

How much does Granite 4.1 3B cost?

Granite 4.1 3B is currently available for free via OpenRouter.

Is Granite 4.1 3B good for coding?

On our coding benchmark index, Granite 4.1 3B ranks #199 of 208 models, placing it in the broader range of the field for code generation and debugging.

Who created Granite 4.1 3B?

Granite 4.1 3B is developed by IBM and was released on April 29, 2026.

© 2026 Design for Online Ltd. Registered in England and Wales No. 10328553. VAT Registered. Design for Online® and Forerunner® are registered trademarks.