Frontier Log

OpenAIModel

GPT-5.2

Made by
OpenAI
Released
Announced in
Introducing GPT-5.2openai.com
Event
GPT-5.2
API record
/api/v1/models/gpt-5-2

Benchmark results

BenchmarkScoreSource check
Humanity's Last ExamNo tools34.5%
CheckedA person checked this number against its source on 16 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
CorroboratedThe same number is printed in 3 other lab documents: 1 2 3
Humanity's Last ExamWith tools · search and Python45.5%
CheckedA person checked this number against its source on 17 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
CorroboratedThe same number is printed in 7 other lab documents, the first 3 linked: 1 2 3
SWE-bench Verified80.0%
CheckedA person checked this number against its source on 16 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
CorroboratedThe same number is printed in 8 other lab documents, the first 3 linked: 1 2 3
SWE-bench Pro55.6%
CheckedA person checked this number against its source on 17 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
CorroboratedThe same number is printed in 5 other lab documents, the first 3 linked: 1 2 3
GPQA Diamondno tools92.4%
CheckedA person checked this number against its source on 16 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
CorroboratedThe same number is printed in 5 other lab documents, the first 3 linked: 1 2 3
BrowseComp65.8%
CheckedA person checked this number against its source on 17 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
CorroboratedThe same number is printed in 7 other lab documents, the first 3 linked: 1 2 3
ARC-AGI-2ARC Prize Verified52.9%
CheckedA person checked this number against its source on 16 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
CorroboratedThe same number is printed in 2 other lab documents: 1 2
Terminal-Bench 2.0harness not stated · reported later, in Introducing GPT-5.462.2%
CheckedA person checked this number against its source on 16 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
CorroboratedThe same number is printed in 2 other lab documents: 1 2
AIME 2025No tools100.0%
CheckedA person checked this number against its source on 18 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
ARC-AGI-1ARC Prize Verified86.2%
CheckedA person checked this number against its source on 18 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
CorroboratedThe same number is printed in 1 other lab document: 1
HMMT February 2025No tools · maximum reasoning effort99.4%
CheckedA person checked this number against its source on 18 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
CorroboratedThe same number is printed in 1 other lab document: 1
Sources

Reported by OpenAI

Events

Stories

All models