Loading activity…
@htihle
AI researcher, I made WeirdML, worried about ASI
AI
The benchmark's creator says that puts it between Sonnet 5.5 and Fable 5.1, but behind the frontier on token efficiency.
AI
A user says its score was close to GPT 5.6 Sol and Fable 5 in a Codex CLI harness run.
AI
A post sharing the results says Sonnet 5.5 scores better than Opus 5, while Grok 4.7 is ahead of Kimi-K3.
AI
The announcement says models must produce results despite limited data, unspecified goals and/or very limited feedback.
AI
The user reports new individual high scores on 6 of 17 tasks and significantly less code than Sol and other recent GPT models, though still more than Claude.
AI
The user reports a new benchmark high, beating Fable 5 (max) by 0.4%, with new records on 3 of the 17 tasks.
