Granite 4.2 30B: benchmark results
IBM's Apache-2.0 30B dense reasoning model from the Granite 4.2 line (August 2026), post-trained from Granite-4.1-30B-Base with a built-in chain-of-thought mode and 128K native context. Provider: IBM. Released 2026-08-25. Access: Open.
Aggregate Rating 1589 ± 35, rank #468 of 1640 rated models, from 89 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA-Omniscience Hallucination Rate | 25.58 | Hallucination Rate (%) | 96 |
| AA-Omniscience Index - Law | -5.7 | Omniscience Index | 75.8 |
| AA-Omniscience Index - Humanities & Social Sciences | -6.7 | Omniscience Index | 71.5 |
| LLM Stats (HMMT25) | 89.17 | Score (%) | 70.4 |
| AA-Omniscience Index - Business | -9.8 | Omniscience Index | 69.1 |
| AA-Omniscience Index - Health | -17 | Omniscience Index | 68.8 |
| AA-Omniscience Index - Software Engineering (SWE) - Julia | -24 | Omniscience Index | 64.2 |
| AA Omniscience | -12.92 | Score | 63.5 |
| AA-Omniscience Index - Science, Engineering & Mathematics | -9.7 | Omniscience Index | 62.8 |
| AA-Omniscience Index - Software Engineering (SWE) - Java | -31 | Omniscience Index | 61.9 |
| AA-Omniscience Index - Software Engineering (SWE) - R | -30 | Omniscience Index | 60 |
| AA-Omniscience Index - Software Engineering (SWE) - Kotlin | -24 | Omniscience Index | 57.1 |
Interactive version: theaggregate.ai/model?slug=granite-4-2-30b · How It Works · Data refreshed daily, snapshot 2026-10-13.