Frontier Log

DeepSeekModel

DeepSeek-V4.1-Flash

Made by
DeepSeek
Released
Announced in
DeepSeek-V4.1-Flash: Smarter, Faster, More Efficientapi-docs.deepseek.com
Event
DeepSeek-V4.1-Flash
API record
/api/v1/models/deepseek-v4-1-flash

Benchmark results

BenchmarkScoreSource check
Humanity's Last ExamNo tools · full set36.8%
CorroboratedThe same number is printed in 3 other lab documents: 1 2 3
text-only subset39.1%
CorroboratedThe same number is printed in 2 other lab documents: 1 2
Humanity's Last ExamWith tools63.9%
CorroboratedThe same number is printed in 2 other lab documents: 1 2
GPQA Diamond90.9%
CorroboratedThe same number is printed in 2 other lab documents: 1 2
Terminal-Bench 4.031.2%
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
AutomationBenchset not stated54.8%
CorroboratedThe same number is printed in 2 other lab documents: 1 2
DeepSWE v1.174.2%
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
Terminal-Bench 2.190.6%
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 DeepSeek

Events

Stories

All models