Frontier Log

Moonshot AIModel

Kimi K3.1 Pro

Made by
Moonshot AI
Released
Announced in
Kimi K3.1 Pro Tech Blog: Advancing Open Intelligencekimi.ai
Event
Kimi K3.1 Pro
API record
/api/v1/models/kimi-k3-1-pro

Benchmark results

BenchmarkScoreSource check
Humanity's Last ExamNo tools · full set; max reasoning effort51.1%
CheckedA person checked this number against its source on 24 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
Humanity's Last ExamWith tools · full set; max reasoning effort70.0%
CheckedA person checked this number against its source on 24 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
GPQA Diamondmax reasoning effort94.2%
CheckedA person checked this number against its source on 24 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
BrowseCompmax reasoning effort; context compaction at 200K tokens; 500-step limit92.1%
CheckedA person checked this number against its source on 24 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
Terminal-Bench 4.0Claude Code harness; max reasoning effort65.7%
CheckedA person checked this number against its source on 24 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
Terminal-Bench Science 0.1Claude Code harness; max reasoning effort38.1%
CheckedA person checked this number against its source on 24 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
DeepSWE v1.1Claude Code harness; max reasoning effort75.5%
CheckedA person checked this number against its source on 24 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
Sources

Reported by Moonshot AI

Events

All models