HealthBench, every mention
1 scene · ← back to HealthBench
tap a year for its mentions
every year anyone Justine Moore 1
Verbatim, from the transcripts: the passages where HealthBench comes up
This Week in AI: GPT-5 Ships, 4o Pulled Back, Grok Imagine Goes Social
- ▶ 11:44 Justine Moore And they talked about how GPT-V was kind of the highest scoring model on this thing called HealthBench, which is, um, a benchmark they trained with like, 250 plus physicians.