Google DeepMind’s recent launch of its AI Co-Mathematician agentic workbench has driven fresh momentum for Gemini models on FrontierMath, the Epoch AI benchmark of unpublished, research-level math problems across four difficulty tiers. The system, built on the Gemini 3.1 family, reached 48% on Tier 4—more than doubling the 19% baseline for Gemini 3.1 Pro and topping other evaluated frontier models. This follows Gemini 3 Pro’s earlier 37–38% scores on the broader FrontierMath set and positions the model competitively against OpenAI’s GPT-5.4 leader at 47.6%. With Epoch AI now auditing roughly one-third of problems for errors and potential June updates, traders are watching for further agentic refinements or a full Gemini 3.1 release that could lift scores before the June 30 resolution window.
Polymarket डेटा का संदर्भ देने वाला प्रयोगात्मक AI-जनरेटेड सारांश। यह ट्रेडिंग सलाह नहीं है और इस बाज़ार के समाधान में कोई भूमिका नहीं निभाता। · अपडेट किया गया$136,324 वॉल्यूम
40%+
86%
45%+
66%
50%+
63%
60%+
54%
$136,324 वॉल्यूम
40%+
86%
45%+
66%
50%+
63%
60%+
54%
This market will resolve according to the Epoch AI’s Frontier Math benchmarking leaderboard (https://epoch.ai/frontiermath) for Tier 1-3. Studies which are not included in the leaderboard (e.g. https://x.com/EpochAIResearch/status/1945905796904005720) will not be considered.
The primary resolution source will be information from EpochAI; however, a consensus of credible reporting may also be used.
बाज़ार खुला: Feb 6, 2026, 6:03 PM ET
Resolver
0x65070BE91...This market will resolve according to the Epoch AI’s Frontier Math benchmarking leaderboard (https://epoch.ai/frontiermath) for Tier 1-3. Studies which are not included in the leaderboard (e.g. https://x.com/EpochAIResearch/status/1945905796904005720) will not be considered.
The primary resolution source will be information from EpochAI; however, a consensus of credible reporting may also be used.
Resolver
0x65070BE91...Google DeepMind’s recent launch of its AI Co-Mathematician agentic workbench has driven fresh momentum for Gemini models on FrontierMath, the Epoch AI benchmark of unpublished, research-level math problems across four difficulty tiers. The system, built on the Gemini 3.1 family, reached 48% on Tier 4—more than doubling the 19% baseline for Gemini 3.1 Pro and topping other evaluated frontier models. This follows Gemini 3 Pro’s earlier 37–38% scores on the broader FrontierMath set and positions the model competitively against OpenAI’s GPT-5.4 leader at 47.6%. With Epoch AI now auditing roughly one-third of problems for errors and potential June updates, traders are watching for further agentic refinements or a full Gemini 3.1 release that could lift scores before the June 30 resolution window.
Polymarket डेटा का संदर्भ देने वाला प्रयोगात्मक AI-जनरेटेड सारांश। यह ट्रेडिंग सलाह नहीं है और इस बाज़ार के समाधान में कोई भूमिका नहीं निभाता। · अपडेट किया गया
बाहरी लिंक से सावधान रहें।
बाहरी लिंक से सावधान रहें।
अक्सर पूछे जाने वाले प्रश्न