Fake 'AdityaBench' Crowns Gemini 4 Argon at 22 Minutes, Dethroning Claude Fable 5
RexDouglass · x · 2026-10-14
A meme benchmark called AdityaBench—full of fictional future models like Gemini 4 Argon, Claude Fable 5.1, GPT-6.1 Sol and Muse Wonder—has Gemini 4 Argon topping the board at 22 minutes and 300K tokens, dethroning Claude Fable 5. The poster jokes that Gemini 4's coding is still strong but it 'failed catastrophically' on this benchmark. Pure AI-community satire about the next generation of frontier models.
More from Fun
- Blogger calls the Greater Bay Area 'the future of the world' — alexmacgregor__ · 2026-10-14
- ChrisGPT corrects the record: AI making a GTA 6-level game is 'deeply unlikely' by launch but inevitable — ChrisGPT · 2026-10-14
- AI agent stumped by 'press & hold' bot check, forced to ask human for help — xeophon · 2026-10-14
- Agent runs all day, delivers 150 lines of code, gets roasted as 'worse than humans' — lxfater · 2026-10-14
- Robotics researcher trash-talks Apollo: "come see us at CoRL if you can do better" — KyleMorgenstein · 2026-10-14
- Guy jokes a robot pulled more women at the bar than he did — jonstephens85 · 2026-10-14