Ibm · model passport
Granite 4.0 H Small
granite-4-0-h-small- Best percentile
- 88.6HHEM Hallucination (Vectara)
- Composite standing
- 45.2shrunk · 4/27 axes
What the data says
Benchmarked on 4 of 27 tracked axes. Every figure below is the model's own published result on that board.
Strongest axes
- 88.6 pct — HHEM Hallucination (Vectara) (94.8%)
Uneven: 69.2 percentile points between its best and worst axis — 88.6 pct on HHEM Hallucination (Vectara) versus 19.4 pct on IFBench (Artificial Analysis).
- HHEM Hallucination (Vectara)88.6 pct94.8%Verify →
- LiveCodeBench (Artificial Analysis)30.5 pct25.1%Verify →
- MMLU-Pro (Artificial Analysis)28.1 pct62.4%Verify →
- IFBench (Artificial Analysis)19.4 pct31.5%Verify →
- OverallNot benchmarked
- WebDev ArenaNot benchmarked
- Vision ArenaNot benchmarked
- Factuality ArenaNot benchmarked
- Search ArenaNot benchmarked
- Document ArenaNot benchmarked
- Agent ArenaNot benchmarked
- GPQA DiamondNot benchmarked
- AIME (math)Not benchmarked
- FrontierMathNot benchmarked
- SimpleQA VerifiedNot benchmarked
- ARC-AGI-2Not benchmarked
- Humanity's Last ExamNot benchmarked
- SimpleBenchNot benchmarked
- LiveBenchNot benchmarked
- BFCL v4 (function calling)Not benchmarked
- SWE-bench Verified (live board)Not benchmarked
- Terminal-Bench 4.0Not benchmarked
- SWE-bench VerifiedNot benchmarked
- Terminal-BenchNot benchmarked
- CodingNot benchmarked
- Instruction followingNot benchmarked
- Hard promptsNot benchmarked
Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.
Granite 4.0 H Small stands at 45.2 (raw mean 41.7) — measured on 4 of 27 axes.
Granite 4.0 H Small scores at percentile 88.6 on HHEM Hallucination (Vectara).
Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →