Frontier Log

AnthropicModel

Claude Opus 5.5

Made by
Anthropic
Released
Announced in
Introducing Claude Opus 5.5anthropic.com
Event
Claude Opus 5.5
API record
/api/v1/models/claude-opus-5-5

Benchmark results

BenchmarkScoreSource check
Humanity's Last ExamNo tools64.4%
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 2 other lab documents: 1 2
Humanity's Last ExamWith tools · max effort67.7%
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 4 other lab documents, the first 3 linked: 1 2 3
SWE-bench Proadaptive thinking, max effort; average of 5 trials · The source doesn't say whether this is the public or the commercial set89.9%
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.
CorroboratedThe same number is printed in 1 other lab document: 1
Terminal-Bench 4.0xhigh effort; standard error ±2.6 points66.4%
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
Terminal-Bench Science 0.1max effort; standard error ±3.5 to 5 points58.7%
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
AutomationBenchrun by Zapier, without fallback models40.0%
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 2 other lab documents: 1 2
run by Zapier; refused tasks re-run with default fallbacks; private set, release 1.0.6 · reported later, in Claude Sonnet 5.5 System Card42.5%
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.
OSWorld 2.1Full set, partial score · max effort; mean of 5 runs; September 10, 2026 task files; the system card labels it OSWorld 2.081.8%
CorroboratedThe same number is printed in 3 other lab documents: 1 2 3
OSWorld 2.1Full set, strict pass rate · max effort; mean of 5 runs; September 10, 2026 task files · reported later, in Claude Sonnet 5.5 System Card48.7%
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.
OSWorld 2.1Offline set, partial score · 82-task offline subset, no internet access; max effort; mean of 5 attempts · reported later, in Claude Haiku 5.5 System Card87.2%
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.
OSWorld 2.1Offline set, strict pass rate · 82-task offline subset, no internet access; max effort; mean of 5 attempts · reported later, in Claude Haiku 5.5 System Card53.2%
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.
FrontierCode 1.1Main set · medium effort; run by Cognition in Claude Code54.6%
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.
max effort · in Introducing Claude Opus 5.554.4%
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 3 other lab documents: 1 2 3
FrontierCode 1.1Extended set · medium effort; run by Cognition in Claude Code65.3%
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.
max effort; run by Cognition in Claude Code63.6%
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.
DeepSWE v1.1average of 5 trials74.2%
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 1 other lab document: 1
Sources

Reported by Anthropic

Events

Stories

All models