Google's Gemini models have driven trader consensus toward high implied probabilities for achieving at least 40% on Humanity's Last Exam—a PhD-level benchmark of 2,500 expert questions testing frontier AI reasoning across math, science, and humanities—following Gemini 3 Deep Think's 48.4% score in February 2026, surpassing prior versions at 37-38%. Rapid iterations like Gemini 3.1 Pro, Flash-Lite, and TTS Preview released through April bolster capabilities in multimodal reasoning and context handling, amid fierce competition from Anthropic's Claude and OpenAI's GPT series. Traders eye Google I/O in May for potential Gemini 4 previews or HLE updates, with resolution hinging on official leaderboard submissions by June 30; delays in scaling or safety constraints could temper gains.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · Updated$307,568 Vol.
50%+
39%
55%+
16%
60%+
11%
$307,568 Vol.
50%+
39%
55%+
16%
60%+
11%
The resolution source will be the official Humanity’s Last Exam leaderboard https://scale.com/leaderboard/humanitys_last_exam.
Market Opened: Jan 29, 2026, 12:50 PM ET
Resolver
0x65070BE91...The resolution source will be the official Humanity’s Last Exam leaderboard https://scale.com/leaderboard/humanitys_last_exam.
Resolver
0x65070BE91...Google's Gemini models have driven trader consensus toward high implied probabilities for achieving at least 40% on Humanity's Last Exam—a PhD-level benchmark of 2,500 expert questions testing frontier AI reasoning across math, science, and humanities—following Gemini 3 Deep Think's 48.4% score in February 2026, surpassing prior versions at 37-38%. Rapid iterations like Gemini 3.1 Pro, Flash-Lite, and TTS Preview released through April bolster capabilities in multimodal reasoning and context handling, amid fierce competition from Anthropic's Claude and OpenAI's GPT series. Traders eye Google I/O in May for potential Gemini 4 previews or HLE updates, with resolution hinging on official leaderboard submissions by June 30; delays in scaling or safety constraints could temper gains.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · Updated
Beware of external links.
Beware of external links.
Frequently Asked Questions