OpenAI's o1 reasoning models command a 98.8% implied probability as the best AI model for math on March 31, fueled by their record-breaking benchmark performance that has left competitors trailing. The o1-preview scored 94.8% on AIME 2024 math problems and 83.3% on the rigorous MATH dataset—leaps ahead of Google's Gemini 1.5 Pro (around 40%) and DeepSeek's offerings (under 70%)—demonstrating superior chain-of-thought reasoning in complex mathematical tasks. This lead, cemented since the September release, reflects trader consensus on sustained AI capabilities amid a quiet competitive landscape, with no verified announcements of rival model upgrades. Realistic challenges include an unforeseen release from Google DeepMind or xAI before evaluation, though timelines and historical delays make this improbable as the deadline nears.
Experimentelle KI-generierte Zusammenfassung mit Polymarket-Daten · AktualisiertOpenAI 98.8%
Google <1%
DeepSeek <1%
Anthropic <1%
$442,615 Vol.
$442,615 Vol.

OpenAI
99%

1%

DeepSeek
<1%

Anthropic
<1%

xAI
<1%

Moonshot
<1%

Z.ai
<1%

Mistral
<1%

Alibaba
<1%
OpenAI 98.8%
Google <1%
DeepSeek <1%
Anthropic <1%
$442,615 Vol.
$442,615 Vol.

OpenAI
99%

1%

DeepSeek
<1%

Anthropic
<1%

xAI
<1%

Moonshot
<1%

Z.ai
<1%

Mistral
<1%

Alibaba
<1%
If two models are tied for the highest LiveBench Mathematics Average score at this market's check time, resolution will be based on whichever company's name, as it is described in this market group, comes first in alphabetical order.
The primary source of resolution for this market will be LiveBench’s AI leaderboard, specifically the “Mathematics Average” category, found at livebench.ai. If this resolution source is unavailable at check time, this market will remain open until the LiveBench AI leaderboard comes back online and will resolve based on the first check after it becomes available. If it becomes permanently unavailable, this market will resolve based on another resolution source.
Markt eröffnet: Dec 12, 2025, 1:25 PM ET
Resolver
0x2F5e3684c...If two models are tied for the highest LiveBench Mathematics Average score at this market's check time, resolution will be based on whichever company's name, as it is described in this market group, comes first in alphabetical order.
The primary source of resolution for this market will be LiveBench’s AI leaderboard, specifically the “Mathematics Average” category, found at livebench.ai. If this resolution source is unavailable at check time, this market will remain open until the LiveBench AI leaderboard comes back online and will resolve based on the first check after it becomes available. If it becomes permanently unavailable, this market will resolve based on another resolution source.
Resolver
0x2F5e3684c...OpenAI's o1 reasoning models command a 98.8% implied probability as the best AI model for math on March 31, fueled by their record-breaking benchmark performance that has left competitors trailing. The o1-preview scored 94.8% on AIME 2024 math problems and 83.3% on the rigorous MATH dataset—leaps ahead of Google's Gemini 1.5 Pro (around 40%) and DeepSeek's offerings (under 70%)—demonstrating superior chain-of-thought reasoning in complex mathematical tasks. This lead, cemented since the September release, reflects trader consensus on sustained AI capabilities amid a quiet competitive landscape, with no verified announcements of rival model upgrades. Realistic challenges include an unforeseen release from Google DeepMind or xAI before evaluation, though timelines and historical delays make this improbable as the deadline nears.
Experimentelle KI-generierte Zusammenfassung mit Polymarket-Daten · Aktualisiert
Vorsicht bei externen Links.
Vorsicht bei externen Links.
Häufig gestellte Fragen