Moonshot AI's July 2026 launch of Kimi K3, a multi-trillion-parameter model with strong tool-use and agentic features, has driven recent sentiment, posting 46.9–56% on Humanity’s Last Exam depending on evaluation protocols. This places the latest Kimi variant near the top of open-weight results but behind Anthropic’s Claude Fable 5.1 and Opus 5 (59–65%) and OpenAI’s GPT-6 Astra (~55%). Earlier Kimi releases like K2.5 and agent variants demonstrated rapid gains via reinforcement learning and parallel tool-calling, yet further 2026 improvements face headroom limits on the 2,500-question graduate-level benchmark. Traders are watching for new Moonshot releases, context-window expansions, or swarm-agent refinements before year-end that could push scores higher.
Résumé expérimental généré par IA à partir des données Polymarket. Ceci n'est pas un conseil de trading et ne joue aucun rôle dans la résolution de ce marché. · Mis à jour$54,462 Vol.
45 % ou plus
74%
50 %+
42%
55 %+
24%
60 %+
11%
65 %+
8%
$54,462 Vol.
45 % ou plus
74%
50 %+
42%
55 %+
24%
60 %+
11%
65 %+
8%
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".
Marché ouvert : Jul 23, 2026, 6:43 PM ET
Source de résolution
https://agi.safe.ai/Résolveur
0x65070BE91...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".
Source de résolution
https://agi.safe.ai/Résolveur
0x65070BE91...Moonshot AI's July 2026 launch of Kimi K3, a multi-trillion-parameter model with strong tool-use and agentic features, has driven recent sentiment, posting 46.9–56% on Humanity’s Last Exam depending on evaluation protocols. This places the latest Kimi variant near the top of open-weight results but behind Anthropic’s Claude Fable 5.1 and Opus 5 (59–65%) and OpenAI’s GPT-6 Astra (~55%). Earlier Kimi releases like K2.5 and agent variants demonstrated rapid gains via reinforcement learning and parallel tool-calling, yet further 2026 improvements face headroom limits on the 2,500-question graduate-level benchmark. Traders are watching for new Moonshot releases, context-window expansions, or swarm-agent refinements before year-end that could push scores higher.
Résumé expérimental généré par IA à partir des données Polymarket. Ceci n'est pas un conseil de trading et ne joue aucun rôle dans la résolution de ce marché. · Mis à jour



Méfiez-vous des liens externes.
Méfiez-vous des liens externes.
Questions fréquentes