OpenAI’s GPT-5.5 series currently leads FrontierMath leaderboards with scores of 51.7–52.4% on the main Tiers 1–4 benchmark of unpublished, research-level math problems, following incremental gains from GPT-5.4. Epoch AI released an updated v2 of the benchmark on June 12 that corrected errors in 42% of problems, potentially altering measured performance for all models. OpenAI funded the benchmark’s creation and retains exclusive access to a subset of problems and solutions, which has supported rapid iteration on its reasoning models. With the June 30 resolution deadline only weeks away, any new model release, API update, or refined evaluation scaffold from OpenAI could shift the highest reported GPT score before markets close.
Résumé expérimental généré par IA à partir des données Polymarket. Ceci n'est pas un conseil de trading et ne joue aucun rôle dans la résolution de ce marché. · Mis à jour$43,059 Vol.
45%+
Yes
50%+
Yes
60%+
Yes
70%+
Yes
$43,059 Vol.
45%+
Yes
50%+
Yes
60%+
Yes
70%+
Yes
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.
Marché ouvert : Jan 29, 2026, 12:47 PM ET
Resolver
0x65070BE91...Résultat proposé: Yes
Aucune contestation
Résultat final: Yes
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...Résultat proposé: Yes
Aucune contestation
Résultat final: Yes
OpenAI’s GPT-5.5 series currently leads FrontierMath leaderboards with scores of 51.7–52.4% on the main Tiers 1–4 benchmark of unpublished, research-level math problems, following incremental gains from GPT-5.4. Epoch AI released an updated v2 of the benchmark on June 12 that corrected errors in 42% of problems, potentially altering measured performance for all models. OpenAI funded the benchmark’s creation and retains exclusive access to a subset of problems and solutions, which has supported rapid iteration on its reasoning models. With the June 30 resolution deadline only weeks away, any new model release, API update, or refined evaluation scaffold from OpenAI could shift the highest reported GPT score before markets close.
Résumé expérimental généré par IA à partir des données Polymarket. Ceci n'est pas un conseil de trading et ne joue aucun rôle dans la résolution de ce marché. · Mis à jour
Méfiez-vous des liens externes.
Méfiez-vous des liens externes.
Questions fréquentes