- Will the highest score achieved by a Moonshot Kimi model on Humanity’s Last Exam in 2026 be 45% or higher?82¢
- Will the highest score achieved by a Moonshot Kimi model on Humanity’s Last Exam in 2026 be 50% or higher?50¢
- Will the highest score achieved by a Moonshot Kimi model on Humanity’s Last Exam in 2026 be 55% or higher?40¢
- Will the highest score achieved by a Moonshot Kimi model on Humanity’s Last Exam in 2026 be 60% or higher?24¢
- Will the highest score achieved by a Moonshot Kimi model on Humanity’s Last Exam in 2026 be 65% or higher?6¢
This market will resolve to "Yes" if any Moonshot Kimi model achieves at least the specified accuracy on Humanity’s Last Exam by December 31, 2026, 11:59 PM ET. Otherwise, this market will resolve to "No". For resolution, “accuracy” refers solely to the value labeled “HLE Accuracy” or a clear equivalent metric if the data’s presentation or terminology is restructured, regardless of the model’s Calibration Error or any other displayed metric. The resolution source will be the official Humanity’s Last Exam leaderboard at https://agi.safe.ai/. If the resolution source becomes unavailable during the listed timeframe, this market will remain open to allow the relevant data to become available again. If the source remains unavailable after the end of the listed timeframe or is otherwise confirmed to be permanently unavailable, official Humanity’s Last Exam results published elsewhere may be used. If no official alternative source is available, this market will resolve to "No".
Moonshot AI’s July 2026 launch of the 2.8-trillion-parameter Kimi K3, featuring native multimodal capabilities, a 1-million-token context window, and strong agentic/tool-use performance, has anchored trader sentiment for the highest Kimi score on Humanity’s Last Exam (HLE) through year-end. The model posted roughly 46.9% on standard HLE evaluations and up to 56% in tool-augmented setups, placing it near the top of open-weight entries but behind leading closed models such as Claude Opus 5 and Fable 5. Ongoing improvements in reasoning scaffolds, fine-tuning of the open-weight release, and continued competition among Chinese labs keep incremental gains plausible before December 31. HLE’s 2,500 expert-authored questions across mathematics, physics, and other domains remain far from saturation, so any further Moonshot updates or optimized inference setups could shift probabilities on thresholds above 50%.