Unverified50% confidenceFactExact time
Gemini-3.1-flash-lite, GPT-6-luna and Claude-Haiku-5.5 are three general-purpose language models; Haiku and luna had thinking steps disabled, Gemini used the provider's default settings, and none of the models were given a persona or strategic advice.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedThe eight models tested include GPT-6 Luna, Claude Haiku 5.5, Gemini 3.5 Flash-Lite, Qwen 3 Next 80B, Gemma 4 31B, GPT-6 Sol, Claude Sonnet 5, and Gemini 3.7 Flash, with each model running 107 investigations per track.74% similarUnverifiedPrime Inference's default model is Gemini 4 Argon, Requesty's is Muse Spark Open, Nvidia's and Nebius Token Factory's is Nemotron 3.5 Super VL, and Aixy's and Neon's is Claude Haiku 5.5.70% similarUnverifiedThe negative lookahead /gemini-2\.5(?!-flash-lite)/i can exclude gemini-2.5-flash-lite, but cannot exclude other non-reasoning-by-default variants that appear in the future (such as gemini-2.5-flash-lite-preview).70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1047720API
curl https://kongchang.com/api/v1/knowledge/claims/1047720MCP
get_claim(id=1047720)