Google DeepMind's recent AI Co-Mathematician agent, built atop Gemini 3.1 Pro, achieved 48% on FrontierMath's grueling Tier 4—doubling the base model's 19% score on unsolved research-level math problems—highlighting agentic scaffolding's potential to boost reasoning capabilities amid tight competition from OpenAI's GPT-5.4 and GPT-5.5 Pro, which lead overall leaderboards at 47.6–52.4%. Base Gemini 3.1 Pro lags at 36–38% on Tiers 1–3, per Epoch AI evaluations, underscoring the benchmark's emphasis on novel problem-solving over memorized patterns. Traders eye Google I/O on May 19–20 for Gemini 4 previews or math-focused updates, with resolution looming by June 30; historical release cadences suggest feasible progress, though timelines often slip and OpenAI dominance persists.
Экспериментальная сводка, созданная ИИ на основе данных Polymarket. Это не является торговой рекомендацией и не влияет на то, как разрешается этот рынок. · ОбновленоОценка Google Gemini в FrontierMath Benchmark к 30 июня?
Оценка Google Gemini в FrontierMath Benchmark к 30 июня?
$136,324 Объем
40%+
86%
45%+
63%
50%+
62%
60%+
54%
$136,324 Объем
40%+
86%
45%+
63%
50%+
62%
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.
Открытие рынка: 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 AI Co-Mathematician agent, built atop Gemini 3.1 Pro, achieved 48% on FrontierMath's grueling Tier 4—doubling the base model's 19% score on unsolved research-level math problems—highlighting agentic scaffolding's potential to boost reasoning capabilities amid tight competition from OpenAI's GPT-5.4 and GPT-5.5 Pro, which lead overall leaderboards at 47.6–52.4%. Base Gemini 3.1 Pro lags at 36–38% on Tiers 1–3, per Epoch AI evaluations, underscoring the benchmark's emphasis on novel problem-solving over memorized patterns. Traders eye Google I/O on May 19–20 for Gemini 4 previews or math-focused updates, with resolution looming by June 30; historical release cadences suggest feasible progress, though timelines often slip and OpenAI dominance persists.
Экспериментальная сводка, созданная ИИ на основе данных Polymarket. Это не является торговой рекомендацией и не влияет на то, как разрешается этот рынок. · Обновлено
Не доверяй внешним ссылкам.
Не доверяй внешним ссылкам.
Часто задаваемые вопросы