Google’s Gemini models hold the current lead on Epoch AI’s FrontierMath benchmark, with Gemini 3 Pro and 3.1 Pro variants posting roughly 38% on Tiers 1–3 and isolated Deep Think or preview runs exceeding 40%, ahead of GPT-5.2 and Claude Opus 4.6 equivalents. With the June 30 resolution date only weeks away, traders price a high probability that at least one Gemini version clears the 40% threshold, driven by the narrow gap and Google DeepMind’s ongoing inference optimizations and internal scaling experiments. Limited runway remains for a new flagship release or training run, while the benchmark’s focus on unpublished, expert-vetted problems makes rapid gains difficult; any official confirmation of a higher score before deadline would serve as the decisive catalyst.
Polymarket 데이터를 참조하는 실험적 AI 생성 요약입니다. 이것은 거래 조언이 아니며 이 마켓의 정산에 영향을 미치지 않습니다. · 업데이트$146,439 거래량
40%+
예
45%+
예
50% 이상
예
60% 이상
예
$146,439 거래량
40%+
예
45%+
예
50% 이상
예
60% 이상
예
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.
마켓 개설일: Feb 6, 2026, 6:03 PM ET
Resolver
0x65070BE91...결과 제안됨: 예
이의 없음
최종 결과: 예
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...결과 제안됨: 예
이의 없음
최종 결과: 예
Google’s Gemini models hold the current lead on Epoch AI’s FrontierMath benchmark, with Gemini 3 Pro and 3.1 Pro variants posting roughly 38% on Tiers 1–3 and isolated Deep Think or preview runs exceeding 40%, ahead of GPT-5.2 and Claude Opus 4.6 equivalents. With the June 30 resolution date only weeks away, traders price a high probability that at least one Gemini version clears the 40% threshold, driven by the narrow gap and Google DeepMind’s ongoing inference optimizations and internal scaling experiments. Limited runway remains for a new flagship release or training run, while the benchmark’s focus on unpublished, expert-vetted problems makes rapid gains difficult; any official confirmation of a higher score before deadline would serve as the decisive catalyst.
Polymarket 데이터를 참조하는 실험적 AI 생성 요약입니다. 이것은 거래 조언이 아니며 이 마켓의 정산에 영향을 미치지 않습니다. · 업데이트
외부 링크에 주의하세요.
외부 링크에 주의하세요.
자주 묻는 질문