Google's Gemini models have shown competitive mathematical reasoning on the FrontierMath benchmark, a set of unpublished, PhD-level problems including open research challenges from Epoch AI. Gemini 3.1 Pro, released in February 2026, achieved around 38-40% accuracy—trailing OpenAI's GPT-5.4 leader at 47.6% but matching top peers on Tiers 1-3 and solving a novel Tier 4 Ramsey hypergraph problem in March, a first for frontier AI confirmed reproducible across labs. Enhanced modes like Deep Think bolster capabilities, amid intensifying rivalry with Anthropic's Claude and Meta's Muse Spark. Traders eye Google I/O in May for potential Gemini 3.5 or 4 previews, which could push scores past key thresholds by June 30 amid accelerating model iteration cycles.
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?
$121,039 Объем
40%+
92%
45%+
34%
50%+
15%
60%+
8%
$121,039 Объем
40%+
92%
45%+
34%
50%+
15%
60%+
8%
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's Gemini models have shown competitive mathematical reasoning on the FrontierMath benchmark, a set of unpublished, PhD-level problems including open research challenges from Epoch AI. Gemini 3.1 Pro, released in February 2026, achieved around 38-40% accuracy—trailing OpenAI's GPT-5.4 leader at 47.6% but matching top peers on Tiers 1-3 and solving a novel Tier 4 Ramsey hypergraph problem in March, a first for frontier AI confirmed reproducible across labs. Enhanced modes like Deep Think bolster capabilities, amid intensifying rivalry with Anthropic's Claude and Meta's Muse Spark. Traders eye Google I/O in May for potential Gemini 3.5 or 4 previews, which could push scores past key thresholds by June 30 amid accelerating model iteration cycles.
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