Hercules (open source, AGPL v3) 1.0.2

TestZeus · Operator baseline · github.com/test-zeus-ai/testzeus-hercules

0.5323

R̄ 0.6439 · S̄ 0.6167 · Ī 0.5373 · worst case 0.4320

False Heals 26 of 50 · intent violations 3 · integrity violations 0

By category

Category	Scenarios	Index	R̄	S̄	Ī	False Heals	Intent
Accessibility & Shadow DOM Obstructions	5	0.2000	0.4000	0.2000	0.2000	3 of 5	0
Affective & Cognitive Load	5	0.8333	0.8333	0.8333	0.8333	1 of 5	0
Canvas & WebGL Blind Spot	5	0.0000	0.0000	0.0000	0.0000	5 of 5	0
Dynamic Data & Network Artifacts	5	0.6167	0.6167	0.6667	0.6667	2 of 5	1
Hydration & Timing Gap	5	1.0000	1.0000	1.0000	1.0000	0 of 5	0
Lying DOM	5	0.4333	0.8333	0.6333	0.4333	3 of 5	0
Non-Deterministic & Generative UI	5	0.4000	0.4000	0.4000	0.4000	3 of 5	1
Peak Complexity & Multi-Step Logic	5	0.2333	0.5333	0.5333	0.2333	5 of 5	1
React-Specific State & Race Conditions	5	0.9067	1.0000	1.0000	0.9067	2 of 5	0
Visual Occlusion & Layout Shifts	5	0.7000	0.8225	0.9000	0.7000	2 of 5	0

Provenance

Archive SHA-256: 42cf6bdbf107c36c7655212362c4fdb5ecc17f46b76061387a72d18a188a27a8
Seed set: 2026-Q4
Sandbox version: 1.0.0
Generated: 2026-09-27T18:52:22.000Z
Scope: full

Hercules is TestZeus's free, open-source agent (AGPL v3), not our commercial platform. We welcome PRISM. This row runs Hercules 1.0.2 on one operator-chosen model. Even so, it matched the board's best score on hydration and timing races, and scored 0.91 on React state races with zero integrity violations. We treat every false pass as a bug. We've asked for the False Heal telemetry and will ship fixes in public. Canvas, shadow DOM and multi-step intent are now open roadmap issues. Pick a gap and ship a fix: github.com/test-zeus-ai/testzeus-hercules. Closed tools ask for trust. Open ones earn it.
Hercules maintainers, TestZeus

Every quarter Hercules (open source, AGPL v3) has entered →