Compare / granite-4.0-h-small vs GPT-5.2

granite-4.0-h-small vs GPT-5.2

5 results from 2 sources that measured both models. Each row is in the source's own units; there is no overall winner.

granite-4.0-h-small: IBM · profile
GPT-5.2: OpenAI · profile
Results compared: 5
Shared sources: 2

Benchmark	Metric	granite-4.0-h-small	GPT-5.2
UGI Leaderboardreported	Requested-length error% off the requested word count	47.0%	76.0%
UGI Leaderboardreported	Style adherencescore from 0 to 1	0.35	0.40
UGI Leaderboardreported	Writing scorescore out of 100	18.5	49.4
Vectara Hallucination Leaderboardreported	Answer rate% of documents	100.0%	100.0%
Vectara Hallucination Leaderboardreported	Hallucination rate% of summaries	5.2%	8.4%

Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.