ModelsCompareBest forBenchmarksStatusPricingAPI

GPT-5.2 Pro

OpenAI·Operational·Released 2025-12-11textvision
Context400k
Max output128k
Input / 1M$21 ↗
Output / 1M$168 ↗
Cached in-
Benchmarks10

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

FrontierMath Tier 4 v2 (Epoch AI run)#13/4446% ↗
FrontierMath Tiers 1-3 v2 (Epoch AI run)#13/5974% ↗
AIME 2025 (no tools)#1/8100% ↗
ARC-AGI-1 (Verified)#3/490.5% ↗
ARC-AGI-2 (Verified)#5/754.2% ↗
BrowseComp#9/1577.9% ↗
GDPval (wins or ties)#5/674.1% ↗
GPQA Diamond#9/7093.2% ↗
Humanity's Last Exam (no tools)#11/2936.6% ↗
Humanity's Last Exam (with tools)#9/1350% ↗

Compare

vs GPT-6 Astravs GPT-5.6 Solvs GPT-5.6 Terravs GPT-5.6 Lunavs Claude Fable 5.1vs Claude Opus 5vs Claude Sonnet 5vs Claude Haiku 4.5

More from OpenAI

GPT-6 AstraGPT-5.6 SolGPT-5.6 TerraGPT-5.6 LunaGPT-5.5GPT-5.5 Pro

Access GPT-5.2 Pro and every other model through one endpoint with automatic failover: Respan gateway.