Kimi K3 and Fable5 nearly tie in AI agent benchmark, combined accuracy reaches 93%
KuCoinFlashShare
Kimi K3 and Fable5 nearly tied in an AI agent benchmark on MetaEra, achieving a combined accuracy of 93% in a Fireworks test. K3 outperformed in security, cryptography, and long-term terminal tasks, while Fable5 excelled in multilingual programming and web development. Fireworks employed "God's-eye routing" to select the optimal and most cost-effective response, with K3 handling 72% to 96% of tasks. K3 also cost up to 50 times less in long-terminal operations. The results are simulated and not yet live. K3 will be open-sourced on Fireworks on July 27. Amid increasing scrutiny under MiCA (EU Markets in Crypto-Assets Regulation), such AI tools could influence liquidity and crypto markets.
Source:Show original
Disclaimer: The information on this page may have been obtained from third parties and does not necessarily reflect the views or opinions of KuCoin. This content is provided for general informational purposes only, without any representation or warranty of any kind, nor shall it be construed as financial or investment advice. KuCoin shall not be liable for any errors or omissions, or for any outcomes resulting from the use of this information.
Investments in digital assets can be risky. Please carefully evaluate the risks of a product and your risk tolerance based on your own financial circumstances. For more information, please refer to our Terms of Use and Risk Disclosure.