OpenAI's GPT-5.6 Sol Achieves 59 Points Using Half the Tokens of Claude Fable 5

According to Artificial Analysis, OpenAI's GPT-5.6 Sol this month achieved a score of 59 on token efficiency benchmarks, consuming approximately 15,000 output tokens per task, compared to Claude Fable 5's 60 points with 33,000 tokens. Despite a per-million-token price of $30, GPT-5.6 Sol's average task cost reached only $1.04, approximately one-third that of Fable 5. The model continues to dominate the Pareto frontier—the efficiency boundary where no competing model can achieve equivalent performance with fewer tokens.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
Lifelikevip
· 10h ago
OpenAI’s GPT-5.6 Sol uses half the tokens with Claude Fable 5 to achieve a 59 score
View OriginalReply0