10 days ago
-
OpenAI Decisions: final doclaynet/forms/tobacco numbers, regroup as generalist+cloud chip (decision-API, not VLM)
-
Add OpenAI Decisions API (gpt-6-luna) row: doclaynet/forms/ood/oov (tobacco not in this HF benchmark)
11 days ago
-
Add latency for nutrient-document-decision
12 days ago
-
Add nutrient-document-decision entry (provisional, latency pending)
25 days ago
-
Add Jev (text-only, cloud chip) to non-VLM tab
-
Re-scored v1 + v2; drop provisional
-
document-classification-leaderboard