Expired80% confidenceBenchmarkExact time
Gemini 4 Argon scores 15% on the hallucination benchmark (lower is better), lower than any current frontier model.
6
Sources
80%
Confidence
Short-term (~14 days)
Relevance
10/5/2026
First Seen
Valid until: 10/19/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedGemini 4 Argon's failure rate on code audit benchmarks ranges between 50% and 70%, with all three independent projects showing high false-positive rates.78% similarUnverifiedIn Artificial Analysis's AA Omniscience test, Argon has a hallucination rate of 15% (the lowest among models with an intelligence index of 45 or above), and an accuracy rate of 50%, lower than Astra's 63%; Argon tends to admit it does not know rather than offering an incorrect guess.75% similarUnverifiedPast Gemini output was limited to approximately 64,000 tokens, and most current frontier models cap a single response at approximately 128,000 tokens; Argon raises the output limit to 1 million tokens.69% similarUnverifiedIn the test fixture, Atlas is the only lead automatically routed to sales (confidence ≥ 0.9 and score ≥ 80); Birch enters manual review; Delta has a confidence of 0.83 and enters manual review even with a high score; Cinder falls below 0.65 and enters the nurturing process.68% similarUnverifiedIn that test, the decision model Jev's accuracy trailed Gemini by only about 1.6 percentage points66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/977888API
curl https://kongchang.com/api/v1/knowledge/claims/977888MCP
get_claim(id=977888)