ModelsCompareBest forBenchmarksStatusPricingAPI

GPT-5.2

OpenAI·Operational·Released 2025-12-11textvision
Context400k
Max output128k
Input / 1M$1.75 ↗
Output / 1M$14 ↗
Cached in$0.175
Benchmarks16

Benchmarks

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

AIME 2025 (MathArena)#1/23100% ↗
AIME 2026 (MathArena)#4/2198.3% ↗
FrontierMath Tier 4 v2 (Epoch AI run)#16/4431.7% ↗
FrontierMath Tiers 1-3 v2 (Epoch AI run)#19/5967.4% ↗
GPQA Diamond (Epoch AI run)#18/7791.4% ↗
OTIS Mock AIME 2024-2025 (Epoch AI run)#17/7696.1% ↗
SimpleQA Verified (Epoch AI run)#30/5337.1% ↗
SWE-bench Verified (Epoch AI run)#11/2473.8% ↗
LMArena Elo#40/621412.4 ↗
AIME 2025 (no tools)#1/8100% ↗
ARC-AGI-1 (Verified)#4/486.2% ↗
ARC-AGI-2 (Verified)#6/752.9% ↗
GDPval (wins or ties)#6/670.9% ↗
GPQA Diamond#14/7092.4% ↗
SWE-Bench Pro#11/1555.6% ↗
SWE-bench Verified#5/4580% ↗

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 and every other model through one endpoint with automatic failover: Respan gateway.