IBM Granite 4.2 8B is an Apache 2.0-licensed dense model with native step-by-step reasoning and specialized training for agentic work. It can plan before acting, sequence tools, navigate codebases, work in terminals, and verify results across coding, search, mathematics, science, and complex instruction-following tasks.
Added Aug 31, 2026
Model weightsContext Window
131.1K
Max Output
N/A
Avg output tokens (7d)
4.3K tokens
Input Price (Auto)
$0.100/1M
Output Price (Auto)
$0.15/1M
Cache Read (Auto)
$0.050/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
11.8
Coding Index
22.4
Agentic Index
3.7
Agentic work
AutomationBench-AA
Workflow automation with guardrail penalties
2.1%
Better than 24% of models compared
AA-Briefcase
Agentic knowledge work (Elo)
320 Elo
Better than 19% of models compared
GDPval-AA v2
Economically valuable tasks (Elo)
645 Elo
Better than 29% of models compared
Document reasoning
GDP.pdf
Professional PDF reasoning: all-pass rate
0.6%
Better than 4% of models compared
AA-LCR v1.1
Long context reasoning with updated grading
45.0%
Better than 43% of models compared
Reasoning
HLE
Humanity's Last Exam
9.7%
Better than 52% of models compared
CritPt
Research-level physics reasoning
0.3%
Coding
Terminal-Bench v4.0
Practical coding and terminal tasks
0.0%
Better than 18% of models compared
SciCode
Python programming for scientific computing
31.5%
Better than 10% of models compared
Knowledge
AA-Omniscience Accuracy
Proportion of correctly answered questions
11.2%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
32.0%
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
63.1%
Better than 38% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
45.0%
Better than 43% of models compared
GDPval-AA (unversioned / legacy)
Economically valuable tasks
7.3%
Last updated Sep 11, 2026
Artificial AnalysisProviders
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Related text models
Compare Granite 4.2 8B with similar models from the same provider or model family.
GPT Astra Latest
openai/gpt-astra-latestCompatibility alias that routes to GPT 6 Astra, the latest supported GPT Astra model.
GPT Luna Latest
openai/gpt-luna-latestCompatibility alias that routes to GPT 5.6 Luna, the latest supported GPT Luna model.
GPT Sol Latest
openai/gpt-sol-latestCompatibility alias that routes to GPT 5.6 Sol, the latest supported GPT Sol model.
GPT Terra Latest
openai/gpt-terra-latestCompatibility alias that routes to GPT 5.6 Terra, the latest supported GPT Terra model.
Fugu Max
sakana/fugu-maxSakana AI's cost-performance Fugu model uses learned multi-agent orchestration to route tasks across expert models for reasoning, coding, and tool use.
Nvidia Nemotron 3.5 Lightning TEE
TEE/nemotron-3.5-lightningNVIDIA's open-weight 30B mixture-of-experts model with 3B active parameters for fast agentic workflows, coding, and tool use. Running inside a TEE (Trusted Execution Environment), with provider attestation support.