ModelsCompareBest forBenchmarksStatusPricingAPI

GPT-4o

OpenAI·Operational·Released 2024-05-13textvision
Context128k
Max output16.384k
Input / 1M$2.5 ↗
Output / 1M$10 ↗
Cached in$1.25
Benchmarks9

Benchmarks

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

AIME 2025 (MathArena)#22/2311.7% ↗
FrontierMath Tiers 1-3 v2 (Epoch AI run)#59/590.4% ↗
GPQA Diamond (Epoch AI run)#74/7749.2% ↗
OTIS Mock AIME 2024-2025 (Epoch AI run)#75/766.4% ↗
SimpleQA Verified (Epoch AI run)#43/5326% ↗
SWE-bench Verified (Epoch AI run)#24/2431% ↗
AIME 2024#6/713.1% ↗
GPQA Diamond#68/7046% ↗
MMLU#8/1485.7% ↗

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-4o and every other model through one endpoint with automatic failover: Respan gateway.