ND ARC-AGI-3 benchmark is out now (arcprize.org)
9 points by pretext 3 days ago | 2 comments on HN ~lite vlite-2.0
Summary ~lite
No safety information could be evaluated due to lack of textual content.
Lite evaluation by llama-4-scout-wai-psq · editorial channel only · no per-section breakdown available
Longitudinal 24 HN snapshots · 2 evals
+1 0 −1 HN
Audit Trail 5 entries
2026-03-25 21:49 eval_success PSQ evaluated: g-PSQ=0.000 (3 dims) - -
2026-03-25 21:49 eval Evaluated by llama-4-scout-wai-psq: 0.00 (Neutral)
2026-03-25 21:49 eval_success Lite evaluated: Neutral (0.00) - -
2026-03-25 21:49 eval Evaluated by llama-4-scout-wai: 0.00 (Neutral)
reasoning
Technical content, zero rights discussion, no transparency indicators visible
2026-03-25 21:49 rater_validation_warn Lite validation warnings for model llama-4-scout-wai: 1W 0R - -