Frontier Log

DeepSeekModel

DeepSeek-V4.1-Flash-1017

Made by
DeepSeek
Released
Announced in
DeepSeek-V4.1-Flash-1017: Wish-Driven Programming Made Realapi-docs.deepseek.com
Event
DeepSeek-V4.1-Flash-1017
API record
/api/v1/models/deepseek-v4-1-flash-1017

Benchmark results

BenchmarkScoreSource check
Humanity's Last ExamNo tools · full set42.6%
CorroboratedThe same number is printed in 1 other lab document: 1
text-only subset44.0%
CorroboratedThe same number is printed in 1 other lab document: 1
Terminal-Bench 4.0Claude Code harness42.3%
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.
AutomationBenchAutomationBench v1.0.660.5%
CorroboratedThe same number is printed in 1 other lab document: 1
DeepSWE v1.1Mini-SWE-V2 harness, max effort77.0%
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.
Sources

Reported by DeepSeek

Events

Modified copies

Stories

All models