Unverified50% confidenceBenchmarkExact time
When given ground coordinates and relation definitions directly, the three models (Claude Opus 5.5, GPT-5.5 and Gemini 3.6 Flash) reach 99% to 100% answer accuracy.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/18/2026
First Seen
Valid until: 12/2/2026
Sources
Related Entities
Related Claims
UnverifiedIn the CV-Bench photo test, when reliable 2D cues are misleading, the accuracy of the three models (Claude Opus 5.5, GPT-5.5 and Gemini 3.6 Flash) likewise drops.73% similarUnverifiedThe median confidence difference across models when fabricating totals is enormous: Gemini 3 Flash and Flash-Lite at 95, GPT-5.4 nano at 62, and Claude Sonnet 5 at only 20.72% similarUnverifiedWhen the BOST instruction is not enabled, the Gemini 3.8 Flash model's accuracy on directly asked questions is about 30% to 60%.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1182630API
curl https://kongchang.com/api/v1/knowledge/claims/1182630MCP
get_claim(id=1182630)