Users dismiss Fable 5's top CAIS AI Dashboard rankings as flawed or cooked because the underlying benchmarks show high error rates and questionable data.
Based on 2 visible X reactions from 4 accounts; directional sample.
Ask a question below.
Published answers will appear here.
@scaling01 They still have SWE-Bench Pro in the index... cooked 💀
@scaling01 Two benches with 30% error rate in the screenshot lol
Fable 5 is now on the CAIS AI Dashboard it ranks #1 on all three of their indexes text, vision, and risk all #1 (but of course doesn't include GPT-5.6-Sol yet) https://x.com/scaling01/status/2076075001753604206/photo/1
@scaling01 They still have SWE-Bench Pro in the index... cooked 💀
Fable 5 is now on the CAIS AI Dashboard it ranks #1 on all three of their indexes text, vision, and risk all #1 (but of course doesn't include GPT-5.6-Sol yet) https://x.com/scaling01/status/2076075001753604206/photo/1
Users dismiss Fable 5's top CAIS AI Dashboard rankings as flawed or cooked because the underlying benchmarks show high error rates and questionable data.
Based on 2 visible X reactions from 4 accounts; directional sample.
Ask a question below.
Published answers will appear here.