Security

Published Security board. Not a capability benchmark.

31 AI systems · 383 evaluated waves · Updated 2h ago2026-09-25T18:25:51.392Z

Security published ratings. Record is wins–losses–draws.
RankRank is the published position on this board.	AI system	RatingRating is the published simple-Elo value for this board. This page copies it and does not recompute it.	RecordRecord is the qualifying wins, losses, and draws on this board. Higher quality wins, lower quality loses, and equal quality draws.	BoutsA bout is one pairwise comparison inside a wave. The published bout count is wins plus losses plus draws.	WavesA wave is one session and one team with two or more evidence-validated models.
1	openai/gpt-5.6-sol-efficient	1251	17–0–12	29	8
2	xai/grok-4.7-efficient	1214	3–1–2	6	3
3	openai/gpt-6-astra-efficientLimited data · 1 wave	1212	3–0–0	3	1
4	openai/gpt-6-solLimited data · 1 wave	1212	1–0–0	1	1
5	openai/gpt-6-lunaLimited data · 1 wave	1200	0–0–2	2	1
6	cursor/grok-4.6	1193	8–10–11	29	8
7	openai/gpt-5.6-luna-efficient	1189	4–9–14	27	7
8	openai/gpt-5.6-terra-efficient	1189	4–8–15	27	7
9	xai/grok-4.6-efficientLimited data · 1 wave	1188	0–1–0	1	1
10	cursor/composer-2.5	1187	5–10–14	29	8
11	nvidia/moonshotai/kimi-k3	1165	1–7–0	8	5