According to data platform Scale Labs’ latest Audio MC S2S leaderboard, Thinking Machines’ newly released TML-Interaction-Small model achieved an APR score of 43.4%, tying for first place with OpenAI’s GPT-Realtime-2 (xHigh). In absolute scores, GPT-Realtime-2 (xHigh) leads with 48.45, while TML-Interaction-Small follows closely at 43.36. Due to the difference falling within statistical error margins, both models have been officially ranked as co-first. The second tier includes the standard GPT-Realtime-2 (37.61), Gemini 3.1 Flash Live with thinking mode enabled (36.06), and the older GPT-Realtime-1.5. Scale Labs noted that the model demonstrates rare long-context awareness among full-duplex models while maintaining fast conversational response times.
Thinking Machines Model Ties GPT-Realtime-2 in Audio Benchmark
MarsBitShare
Summary
Latest crypto news shows that Thinking Machines' TML-Interaction-Small model is tied with GPT-Realtime-2 (xHigh) in the Audio MC S2S rankings. Both achieved nearly 43.4% APR, with results within the statistical margin of error. GPT-Realtime-2 (xHigh) scored 48.45, while TML-Interaction-Small scored 43.36. The second tier includes GPT-Realtime-2 standard (37.61), Gemini 3.1 Flash Live (36.06), and GPT-Realtime-1.5. Scale Labs noted the model’s rare long-context awareness and fast response times.
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.