‹ BackHN Continuity

History

DoGBench: The first user-facing docs generation benchmark. No model scores >50%

Open thread

First rank
29
Best rank
29
Last rank
30
Observations
3
First seen
1790899574
Last seen
1790900361
Missing captures
0
Milestones
0

Top is rank 1. Gaps between captures are not reconstructed.

  1. Rank 30

    5 points · 2 comments · observed

  2. Rank 29

    5 points · 1 comments · observed

  3. Rank 29

    4 points · 1 comments · observed

Unofficial Hacker News client; not affiliated with Y Combinator.