ModelsCompareBest forBenchmarksStatusPricingAPI

o3

OpenAI·Operational·Released 2025-04-16textvision
Context200k
Max output100k
Input / 1M$2 ↗
Output / 1M$8 ↗
Cached in$0.5
Benchmarks7

Benchmarks

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

AIME 2025 (MathArena)#10/2389.2% ↗
FrontierMath Tiers 1-3 v2 (Epoch AI run)#43/5933.3% ↗
GPQA Diamond (Epoch AI run)#53/7781.8% ↗
OTIS Mock AIME 2024-2025 (Epoch AI run)#47/7684.4% ↗
SimpleQA Verified (Epoch AI run)#16/5349.4% ↗
SWE-bench Verified (Epoch AI run)#19/2462.3% ↗
SWE-bench Verified#33/4569.1% ↗

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 o3 and every other model through one endpoint with automatic failover: Respan gateway.