Google’s latest Gemini iterations continue to lead the Humanity’s Last Exam leaderboard, with the Gemini 3.1 Pro Preview recently posting a 44.7% score on the 2,500-question expert benchmark designed to test frontier reasoning across math, physics, biology, and other disciplines. Steady gains since Gemini 3 Pro’s 37.5–38.3% results in late 2025 reflect targeted advances in long-horizon planning and tool use, outpacing OpenAI’s GPT-5.5 variants that sit just behind at 44.3%. With June 30 only weeks away, traders are watching for any final model updates or “thinking” mode enhancements that could push scores higher before the cutoff, while noting that benchmark saturation and evaluation methodology shifts remain key variables in this fast-moving artificial intelligence race.
Experimentelle KI-generierte Zusammenfassung mit Polymarket-Daten. Dies ist keine Handelsberatung und spielt keine Rolle bei der Auflösung dieses Marktes. · AktualisiertGoogle Gemini-Punktzahl bei der letzten Prüfung der Menschheit bis zum 30. Juni?
$312,759 Vol.
50 %+
56%
55 %+
26%
60 %+
6%
$312,759 Vol.
50 %+
56%
55 %+
26%
60 %+
6%
The resolution source will be the official Humanity’s Last Exam leaderboard https://scale.com/leaderboard/humanitys_last_exam.
Markt eröffnet: 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 latest Gemini iterations continue to lead the Humanity’s Last Exam leaderboard, with the Gemini 3.1 Pro Preview recently posting a 44.7% score on the 2,500-question expert benchmark designed to test frontier reasoning across math, physics, biology, and other disciplines. Steady gains since Gemini 3 Pro’s 37.5–38.3% results in late 2025 reflect targeted advances in long-horizon planning and tool use, outpacing OpenAI’s GPT-5.5 variants that sit just behind at 44.3%. With June 30 only weeks away, traders are watching for any final model updates or “thinking” mode enhancements that could push scores higher before the cutoff, while noting that benchmark saturation and evaluation methodology shifts remain key variables in this fast-moving artificial intelligence race.
Experimentelle KI-generierte Zusammenfassung mit Polymarket-Daten. Dies ist keine Handelsberatung und spielt keine Rolle bei der Auflösung dieses Marktes. · Aktualisiert
Vorsicht bei externen Links.
Vorsicht bei externen Links.
Häufig gestellte Fragen