Granite 4.2 30B.
Open weights Flagship
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| IFBench | 77.2% | #14 of 80 | Lab model card | |
| Arena-Hard v2.0 | 67.9% | #13 of 24 | Lab model card | |
| LMArena (Elo) | 1,340 | #189 of 335 | Official leaderboard | |
| MMLU-Pro | 77.6% | #96 of 167 | Lab model card | |
| RULER | 81.4% | #32 of 42 | Lab model card | |
| MMLU-ProX | 66.6% | #18 of 23 | Lab model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AIME 2025 | 89.2% | #54 of 143 | Lab model card | |
| HMMT 2025 | 89.2% | #25 of 54 | Lab model card | |
| GPQA Diamond | 66.4% | #198 of 302 | Lab model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LiveCodeBench v6 | 75.8% | #43 of 90 | Lab model card | |
| SciCode | 38.8% | #31 of 49 | Lab model card | |
| SWE-bench Verified | 57% | #117 of 155 | Lab model card | |
| Bird-SQL | 41.9% | #10 of 13 | Lab model card | |
| SWE-bench Multilingual | 41.9% | #70 of 73 | Lab model card | |
| SWE-Bench Pro | 33.3% | #80 of 81 | Lab model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BFCL V4 | 61.4% | #19 of 30 | Lab model card | |
| tau3-bench | 62% | #11 of 14 | Lab model card | |
| Terminal-Bench 2.1 | 29.2% | #54 of 56 | Lab model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GDPval-AA v2 | 1,225 | #22 of 27 | Lab model card | |
| ProfBench | 42.9% | #2 of 2 | Lab model card |
The Self-Reported Index fits one score to the 17 capability results IBM reported for this model, on the scale of the Epoch Capabilities Index. Labs choose which benchmarks to show and how to run them, so read it as the lab's claim, not an independent measurement. The 90% interval runs from 134.1 to 138.8. How we compute it.
The benchmarks the lab chose to headline, with the scores it gave.