Unverified50% confidenceBenchmarkExact time
At maximum reasoning effort, the model's success rate on the LIBERO benchmark is close to the level of GPT-6 Astra and GPT-6.1 Sol.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/16/2026
First Seen
Valid until: 2/14/2027
Sources
Related Entities
Related Claims
UnverifiedThe Quant-Arena paper evaluates nine frontier models, with GPT-6 Astra scoring the highest.78% similarUnverifiedIn the Exploit Gym benchmark, the previous-generation GPT-5.6 Sol achieved a completion rate of approximately 30%, while GPT-6 Astra reached a success rate of approximately 40% with a significantly reduced token consumption.77% similarVerifiedGPT-6 Astra is notably different from previous model iterations, being powerful in certain respects while showing little improvement or even appearing to regress in other scenarios.77% similarUnverifiedWhen reasoning is set to High, GPT-6.1 Sol scores highest in professional work and scientific research scenarios, far surpassing Opus 5.5 in scientific research77% similarUnverifiedWilliam Liu compared the tokenization results of multiple GPT models using a set of fixtures, with the experiment covering seven GPT models, including GPT-5.5, three variants of GPT-5.6 (Sol/Terra/Luna), and three variants of GPT-6 (Astra/Sol/Luna).77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1175125API
curl https://kongchang.com/api/v1/knowledge/claims/1175125MCP
get_claim(id=1175125)