Google's Gemini 3.1 Pro Preview currently leads the Humanity’s Last Exam leaderboard with 44.7% accuracy on this frontier benchmark of 2,500 PhD-level questions spanning mathematics, sciences, and humanities, outpacing OpenAI's GPT-5.5 variants at 44.3% and below. Released in February 2026, this large language model iteration introduced enhanced "thinking high" reasoning modes that boosted performance on challenging closed-ended evaluations, signaling Google's competitive edge in AI capabilities amid intensifying rivalry with Anthropic's Claude and xAI's Grok. No leaderboard updates in the past 30 days, but trader sentiment reflects expectations of iterative gains. Key catalyst: Google I/O on May 19-20, where Gemini advancements or previews could elevate scores toward 50% by June 30 resolution, though benchmark saturation risks persist.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · Updated$310,437 Vol.
50%+
56%
55%+
12%
60%+
8%
$310,437 Vol.
50%+
56%
55%+
12%
60%+
8%
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 3.1 Pro Preview currently leads the Humanity’s Last Exam leaderboard with 44.7% accuracy on this frontier benchmark of 2,500 PhD-level questions spanning mathematics, sciences, and humanities, outpacing OpenAI's GPT-5.5 variants at 44.3% and below. Released in February 2026, this large language model iteration introduced enhanced "thinking high" reasoning modes that boosted performance on challenging closed-ended evaluations, signaling Google's competitive edge in AI capabilities amid intensifying rivalry with Anthropic's Claude and xAI's Grok. No leaderboard updates in the past 30 days, but trader sentiment reflects expectations of iterative gains. Key catalyst: Google I/O on May 19-20, where Gemini advancements or previews could elevate scores toward 50% by June 30 resolution, though benchmark saturation risks persist.
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