Unverified50% confidenceBenchmarkExact time
On the core leaderboard of 13 visual questions, GPT-6 Astra ranked first with 63 points, while Gemini 3.8 Flash came in last.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/24/2026
First Seen
Valid until: 11/7/2026
Sources
Can AI Recognize the Laughing Milk Dragon? Testing 11 Models with the Milk Frog Bench
bilibili伍斯特饿10/23/2026
Related Entities
Related Claims
UnverifiedOn the Frontier SWE benchmark, GPT-6 Astra scores 65.5, ahead of Gemini 4 Argon's 55.78% similarUnverifiedGemini 4 Argon ranks first on the Arena text leaderboard, but ninth on the WebDev leaderboard voted on by real websites, where Claude Opus 5.5 is first and GPT-6 Astra second.74% similarUnverifiedGemini 4's hallucination rate is 15%, while GPT-6 Astra's hallucination rate is 51%.72% similarVerifiedGemini 4 Argon ties with GPT-6 Astra on the Artificial Analysis Intelligence Index.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1092317API
curl https://kongchang.com/api/v1/knowledge/claims/1092317MCP
get_claim(id=1092317)