Frontier Log

AnthropicModel

Claude Opus 4.1

Made by
Anthropic
Released
Announced in
Claude Opus 4.1anthropic.com
Event
Claude Opus 4.1
API record
/api/v1/models/claude-opus-4-1

Benchmark results

BenchmarkScoreSource check
Humanity's Last ExamNo tools · reasoning only; decontamination improved with Opus 4.5, which may affect this score · reported later, in Claude Opus 4.5 System Card14.2%
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.
Humanity's Last ExamWith tools · with search · reported later, in Claude Opus 4.5 System Card22.7%
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.
SWE-bench Verifiedbash and editor tools; averaged over 10 trials; no test-time compute74.5%
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 4 other lab documents, the first 3 linked: 1 2 3
GPQA Diamondextended thinking up to 64K tokens80.9%
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.
reported later, in Introducing Claude Opus 4.581.0%
CorroboratedThe same number is printed in 2 other lab documents: 1 2
AIME 2025No tools · extended thinking up to 64K tokens78.0%
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.
Terminal-Bench 1.0no extended thinking; Terminus 1 agent; averaged over 5 trials43.3%
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.
Sources

Reported by Anthropic

Events

Stories

All models