Google Gemini 3.1 Pro Preview currently leads the official Scale AI Humanity's Last Exam leaderboard at 46.44% accuracy—the toughest frontier benchmark with 2,500 expert-level questions across math, science, and humanities—surpassing OpenAI's GPT-5.4 Pro at 44.32% via advanced "thinking high" reasoning chains. This reflects Google's rapid iteration, jumping from Gemini 3 Pro's 37.5% in late 2025 to near-50% peaks like Deep Think's 48.4% in February 2026, bolstering trader consensus on breaching 50% amid scaling laws and post-training optimizations. Competitive pressure mounts from xAI's Grok-4 claims of 50.7% and Anthropic's Claude variants; Google I/O on May 19-20 may unveil Gemini 3.2 enhancements targeting higher thresholds before the June 30 resolution deadline.
Resumo experimental gerado por IA com dados do Polymarket. Isto não é aconselhamento de trading e não tem qualquer papel na resolução deste mercado. · AtualizadoPontuação do Google Gemini no último exame da Humanidade até 30 de junho?
Pontuação do Google Gemini no último exame da Humanidade até 30 de junho?
$312,088 Vol.
50%+
65%
55%+
28%
60%+
6%
$312,088 Vol.
50%+
65%
55%+
28%
60%+
6%
The resolution source will be the official Humanity’s Last Exam leaderboard https://scale.com/leaderboard/humanitys_last_exam.
Mercado Aberto: 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 Gemini 3.1 Pro Preview currently leads the official Scale AI Humanity's Last Exam leaderboard at 46.44% accuracy—the toughest frontier benchmark with 2,500 expert-level questions across math, science, and humanities—surpassing OpenAI's GPT-5.4 Pro at 44.32% via advanced "thinking high" reasoning chains. This reflects Google's rapid iteration, jumping from Gemini 3 Pro's 37.5% in late 2025 to near-50% peaks like Deep Think's 48.4% in February 2026, bolstering trader consensus on breaching 50% amid scaling laws and post-training optimizations. Competitive pressure mounts from xAI's Grok-4 claims of 50.7% and Anthropic's Claude variants; Google I/O on May 19-20 may unveil Gemini 3.2 enhancements targeting higher thresholds before the June 30 resolution deadline.
Resumo experimental gerado por IA com dados do Polymarket. Isto não é aconselhamento de trading e não tem qualquer papel na resolução deste mercado. · Atualizado
Cuidado com os links externos.
Cuidado com os links externos.
Frequently Asked Questions