Google DeepMind's Gemini 3.1 Pro maintains competitive positioning on the FrontierMath benchmark, scoring comparably to Gemini 3 Pro's prior record of 38% on Tiers 1–3 and 19% on the ultra-challenging Tier 4, while newly solving one previously unsolved Tier 4 problem, as reported by Epoch AI in February 2026. This follows the February 12 launch of Gemini 3 Deep Think, a reasoning mode upgrade excelling in math and scientific benchmarks like IMO Gold standard, narrowing gaps with OpenAI's GPT-5.4 (current leaderboard leader at 47.6%). Trader sentiment hinges on Google's rapid iteration pace amid fierce AI rivalry, with potential catalysts including May's Google I/O announcements or fresh evaluations before the June 30 deadline; historical slips in model timelines add uncertainty to scaling FrontierMath scores beyond 50%.
基於Polymarket數據的AI實驗性摘要 · 更新於$48,923 交易量
40%+
94%
45% 以上
70%
50%+
60%
60%+
11%
$48,923 交易量
40%+
94%
45% 以上
70%
50%+
60%
60%+
11%
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.
市場開放時間: 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 Gemini 3.1 Pro maintains competitive positioning on the FrontierMath benchmark, scoring comparably to Gemini 3 Pro's prior record of 38% on Tiers 1–3 and 19% on the ultra-challenging Tier 4, while newly solving one previously unsolved Tier 4 problem, as reported by Epoch AI in February 2026. This follows the February 12 launch of Gemini 3 Deep Think, a reasoning mode upgrade excelling in math and scientific benchmarks like IMO Gold standard, narrowing gaps with OpenAI's GPT-5.4 (current leaderboard leader at 47.6%). Trader sentiment hinges on Google's rapid iteration pace amid fierce AI rivalry, with potential catalysts including May's Google I/O announcements or fresh evaluations before the June 30 deadline; historical slips in model timelines add uncertainty to scaling FrontierMath scores beyond 50%.
基於Polymarket數據的AI實驗性摘要 · 更新於
警惕外部連結哦。
警惕外部連結哦。
Frequently Asked Questions