Granite 4.2 30B
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 rankingsPublished scores only, each linked to its source. Ticks are every other model's best published score.
GPQA Diamond
PhD-level scientific reasoning, pass@1, no tools
64.4%, source: Artificial AnalysisRanks 160th of 221 models with a score
Humanity's Last Exam (text-only)
Reasoning & knowledge, no tools
11.2%, source: Artificial AnalysisRanks 128th of 221 models with a score
τ³-Banking
Agentic tool use with knowledge retrieval (banking)
14.4%, source: Artificial AnalysisRanks 57th of 103 models with a score
Terminal-Bench 2.1 (Terminus 2)
Agentic coding & terminal use
26.6%, source: Artificial AnalysisRanks 89th of 127 models with a score
SciCode (with background)
Scientific coding
37.8%, source: Artificial AnalysisRanks 96th of 118 models with a score
GDPval-AA v2.1 (Elo)
Real-world work tasks; a rating against other models, not a percentage
575, source: Artificial AnalysisRanks 97th of 144 models with a score
LCR
Long-context reasoning, AA-LCR v1.1
49%, source: Artificial AnalysisRanks 129th of 211 models with a score
Omni Accuracy
Omniscience knowledge accuracy
10.1%, source: Artificial AnalysisRanks 184th of 216 models with a score
Non-Hallucination
1 − hallucination rate
74.4%, source: Artificial AnalysisJoint 13th of 216 models with a score
Show as table
| Benchmark | Score |
|---|---|
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
- Granite 4.0 1B128k · GPQA 28.1%
- Granite 4.0 350M32k · GPQA 26.1%
- Granite 4.0 H 1B128k · GPQA 26.3%
- Granite 4.0 H 350M32k · GPQA 25.7%
- Granite 4.0 H Small128k · GPQA 41.6%
- Granite 4.0 Micro128k · GPQA 33.6%
- Granite 4.1 30B131k · GPQA 48.1%
- Granite 4.1 3B131k · GPQA 31.4%
- Granite 4.1 8B131k · GPQA 43.3%
- Granite 4.2 3B128k · GPQA 55.9%
- Granite 4.2 8B128k · GPQA 63.1%