Dhruv Batra(@DhruvBatra_):The most valuable bit of information in an eval is often — which method is #2? (Because the #1 spot faced a strong selection pressure) For instance, what this plot conveys is a confirmation from Anthropic that GPT 5.6 Sol pareto-dominates Fable 5 on coding benchmarks.

Dhruv Batra

@DhruvBatra_

Co-founder & Chief Scientist @yutori_ai. Prev: Senior Director leading FAIR Embodied AI @MetaAI and Professor @GeorgiaTech.

参加 January 2016

754 フォロー中 21.4K ファン

Dhruv Batra@DhruvBatra_

2026.07.24 19:19

The most valuable bit of information in an eval is often — which method is #2#? (Because the #1# spot faced a strong selection pressure) For instance, what this plot conveys is a confirmation from Anthropic that GPT 5.6 Sol pareto-dominates Fable 5 on coding benchmarks.