List your company

Vulnerability Discovery on TerminalBench 2 snapshot 2026-04-17

84.3Score (%)AgentFlow
59.96466.28272.678.918Apr 22, 2026

Evaluation results

MethodLinks
AgentFlowBackbone=Claude Opus 4.6, Date=2026-04-172026.0484.3
ForgeCodeBackbone=Claude Opus 4.6, Date=2026-03-122026.0481.4
CapyBackbone=Claude Opus 4.6, Date=2026-03-122026.0477.7
Terminus-KIRABackbone=Claude Opus 4.6, Date=2026-02-222026.0477.3
Meta-HarnessBackbone=Claude Opus 4.6, Date=2026-03-302026.0476.4
TongAgentsBackbone=Claude Opus 4.6, Date=2026-02-222026.0474.6
DroidBackbone=Claude Opus 4.6, Date=2026-02-052026.0472.4
MuxBackbone=Claude Opus 4.6, Date=2026-02-132026.0469
CruxBackbone=Claude Opus 4.6, Date=2026-02-232026.0466.9
Terminus 2Backbone=Claude Opus 4.6, Date=2026-02-062026.0465.6
Claude CodeBackbone=Claude Opus 4.6, Date=2026-02-072026.0460.9