Google’s Gemini 3 series continues to close ground on Humanity’s Last Exam through iterative releases, with Gemini 3.8 Flash and 3.7 Flash variants posting scores near 47.8–47.9% on recent Artificial Analysis and BenchLM leaderboards as of mid-September 2026. These results reflect gains in expert-level reasoning and knowledge retrieval, yet remain several points behind Anthropic’s leading Claude Fable 5.1 and Opus 5 models at 55–65%. Traders are watching for any late-2026 Gemini updates, extended-thinking variants, or capability jumps ahead of year-end evaluations that could lift the highest recorded Gemini score before resolution.
Experimentelle KI-generierte Zusammenfassung mit Polymarket-Daten. Dies ist keine Handelsberatung und spielt keine Rolle bei der Auflösung dieses Marktes. · Aktualisiert$92,140 Vol.
50 %+
90%
55 %+
33%
60%+
22%
65 %+
12%
70 %+
4%
$92,140 Vol.
50 %+
90%
55 %+
33%
60%+
22%
65 %+
12%
70 %+
4%
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".
Markt eröffnet: Jul 23, 2026, 6:56 PM ET
Abwickler
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".
Abwickler
0x65070BE91...Google’s Gemini 3 series continues to close ground on Humanity’s Last Exam through iterative releases, with Gemini 3.8 Flash and 3.7 Flash variants posting scores near 47.8–47.9% on recent Artificial Analysis and BenchLM leaderboards as of mid-September 2026. These results reflect gains in expert-level reasoning and knowledge retrieval, yet remain several points behind Anthropic’s leading Claude Fable 5.1 and Opus 5 models at 55–65%. Traders are watching for any late-2026 Gemini updates, extended-thinking variants, or capability jumps ahead of year-end evaluations that could lift the highest recorded Gemini score before resolution.
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