Frontier Log

Benchmark · Active

Agents' Last Exam v1.1

Created by UC Berkeley RDI, 14 Oct 2026 · Higher is better · Website

0102030405060Oct 202644.2%Kimi K3.1 Pro0102030405060Oct 202644.2%Kimi K3.1 Pro

Results

ModelScoreSourceSource check
Kimi K3.1 Pro24 Oct 2026 · Moonshot AI44.2%Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence86-task CLI subset; Kimi Code harness; max effort; runs that bypass task requirements scored zero

All benchmarks