HomeAI · summaries
Storia in 2 fonti
OpenAI launches LifeSciBench to evaluate AI in life sciences
OpenAI launched LifeSciBench with 750 expert-authored tasks and 19,020 evaluation criteria to benchmark AI models like GPT-Rosalind on real life sciences
Confronto fonti
2 prospettive sulla stessa storiaTimeline cronologica
- ·
cryptobriefing.com
OpenAI launches LifeSciBench to evaluate AI in life sciences
OpenAI launched LifeSciBench with 750 expert-authored tasks and 19,020 evaluation criteria to benchmark AI models like GPT-Rosalind on real life sciences
- ·
marktechpost.com
OpenAI Releases LifeSciBench, a 750-Task Benchmark Grading AI Models on Real Life-Science Research With Expert-Written Rubric
OpenAI's LifeSciBench grades AI models on 750 expert-authored life-science tasks using rubrics; the strongest model passes only 36.1%.