If a single model is reported to achieve a score of 90% or higher on the GPQA evaluation, as noted on the official leaderboard.
Resolves Yes if If a single model is reported to achieve a score of 90% or higher on the GPQA evaluation, as noted on the official leaderboard.
Outcome verified from github.com.
Trading on material non-public information is prohibited. Markets are for entertainment and informational purposes using free Pulse Credits — no real-money wagering. If you believe a participant has acted on inside information, please report it.
Analyzing this market…