Frontier Log

OpenAIModel

GPT-5.5

Made by
OpenAI
Released
Announced in
Introducing GPT-5.5openai.com
Event
GPT-5.5
API record
/api/v1/models/gpt-5-5

Benchmark results

BenchmarkScoreSource check
Humanity's Last ExamNo tools41.4%
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 6 other lab documents, the first 3 linked: 1 2 3
Humanity's Last ExamWith tools52.2%
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 6 other lab documents, the first 3 linked: 1 2 3
SWE-bench Pro58.6%
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 7 other lab documents, the first 3 linked: 1 2 3
reported later, in GPT-5.6: Frontier intelligence that scales with your ambition59.4%
CheckedA person checked this number against its source on 20 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
GPQA Diamond93.6%
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 2 other lab documents: 1 2
BrowseComp84.4%
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 Verified85.0%
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.
Terminal-Bench 2.082.7%
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.
AutomationBenchreported later, in GPT-5.6: Frontier intelligence that scales with your ambition12.9%
CorroboratedThe same number is printed in 1 other lab document: 1
OSWorld-Verified78.7%
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 6 other lab documents, the first 3 linked: 1 2 3
ARC-AGI-1ARC Prize Verified95.0%
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-3reported later, in GPT-5.6: Frontier intelligence that scales with your ambition0.43%
CheckedA person checked this number against its source on 20 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
Sources

Reported by OpenAI

Events

Stories

All models