Skip to main content
MANIFOLD
OpenAI Astra Prop Bets
35
Ṁ250Ṁ4.2k
Oct 2
80%
Resolves a FrontierMath Open Problems "Solid Result" or Higher Within One Month of Release
98.8%
OpenAI claims it is AGI within one week of release

All benchmarks (except for Artificial Analysis and Frontier Math Open Problems) will resolve according to what OpenAI claims Astra scores on them. In Lieu of that, I will look to third-party benchmarking, prioritizing the benchmark's official leaderboard (like https://www.terminal-bench-science.ai/ for terminal bench science)

TERMINAL-BENCH-SCIENCE
A benchmark for evaluating AI agents on research workflows across scientific domains
Market context
AI
OpenAI
AI Impacts
Technical AI Timelines
Prop Bets
Get
Ṁ1,000
to start trading!

People are also trading

Sort by:
bought Ṁ75 YES

OpenAI just claimed it's AGI, OpenAI president and cofounder Greg Brockman answered the question about whether Astra qualifies as AGI in an OpenAI press briefing; he said:

“I think we’re there.”

@JasonMendoza2008 @JaundicedBaboon also they said Welcome to the AGI Era here: Just a moment...

@JasonMendoza2008 if no other statements or clarifications are made within the week I’ll resolve yes based on this

bought Ṁ110 YES

@JaundicedBaboon can we resolve the ones that need to be resolved

has anyone read the system card? gpt 6 astra in fact did score slightly lower than 5.6 sol on a some specific safety benchmarks https://deploymentsafety.openai.com/gpt-6-astra/static-jailbreak-evaluations

bought Ṁ100 YES

@EvanWang11j3

indeed you're right, thanks for the free mana I guess lol

I meant to allow others to add questions but I forgot 😭

People are also trading