Granite 4.2 30B

Open weights128k context

Granite 4.2 30B is an open-weights model from IBM with a 128k-token context window. No provider we track lists it yet.

Providers serving Granite 4.2 30B

No provider we track lists this model yet.

Granite 4.2 30B benchmark scores

Compare every model in Bench rankings

Published scores only, each linked to its source. Ticks are every other model's best published score.

Show as table
Benchmark scores for Granite 4.2 30B
BenchmarkScore
GPQA Diamond
PhD-level scientific reasoning, pass@1, no tools
64.4%, source: Artificial Analysis
Humanity's Last Exam (text-only)
Reasoning & knowledge, no tools
11.2%, source: Artificial Analysis
τ³-Banking
Agentic tool use with knowledge retrieval (banking)
14.4%, source: Artificial Analysis
Terminal-Bench 2.1 (Terminus 2)
Agentic coding & terminal use
26.6%, source: Artificial Analysis
SciCode (with background)
Scientific coding
37.8%, source: Artificial Analysis
GDPval-AA v2.1 (Elo)
Real-world work tasks; a rating against other models, not a percentage
575, source: Artificial Analysis
LCR
Long-context reasoning, AA-LCR v1.1
49%, source: Artificial Analysis
Omni Accuracy
Omniscience knowledge accuracy
10.1%, source: Artificial Analysis
Non-Hallucination
1 − hallucination rate
74.4%, source: Artificial Analysis

More from IBM

QAI lists these prices; it does not serve or resell these models. Prices are each provider's standard on-demand list price in US dollars per million tokens (default region, standard tier, peak hours, base context tier), checked on the date shown against the provider's own published prices or, where it has no public price page, its listing on OpenRouter. Most benchmark scores come from Artificial Analysis; Epoch AI (GPQA Diamond), MathArena (AIME 2026) and the APEX-Agents and CritPt leaderboards add the rest, and where none of them has a model, or none ran it at full capability, a figure its maker published may stand in (marked v); in some benchmarks it was run the maker's own way, which its note names. Each benchmark follows one test setup, the one used by the source that covers the most models, and leaves results from other setups out. Each score is the best its source published across the model's settings, names any non-default setting, and links to its source.

An AIME 2026 score noted “released after the exam” comes from a model released after the exam, so the problems may have been in its training data. GDPval-AA is a rating against other models (Elo), not a percentage. Data as of 26 Oct 2026.

Sources and licences