adi

@adonis_singh

18 • probing LLMs • prev @lmstudio

A user says Anthropic holds all three top spots on the AA Benchmark and calls its showing strong even with a mid-tier model.

12 Sources, 20d ago, updated 20d ago

Engineer Adonis Singh posted a leaderboard screenshot comparing astra max and sol max models.

7 Sources, 46d ago, first seen 46d ago

18-year-old LLM engineer shares surprise at new model's benchmark results.

1 Source, 46d ago, first seen 46d ago

Official OpenAI accounts post model scores and task capabilities.

25 Sources, 47d ago, first seen 47d ago

Engineer reports largest gain yet for the model on visual benchmark.

2 Sources, 49d ago, first seen 49d ago

Featured in