Frontier Log

Benchmark · Active

Agents' Last Exam v1.1

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

0102030405060Oct 202643.2%Kimi K3.1 Pro0102030405060Oct 202643.2%Kimi K3.1 Pro

Settings and run setups

Task setScoringProviders
All tasks (122)ScoreGoogle
All tasks (122)Pass rateTencent
All tasks (122)Not statedMoonshot AI
CLI subset (86)Not statedMoonshot AI
Not statedNot statedAlibabaMeituan

Download image

Results

ModelScoreSource
Kimi K3.1 Pro24 Oct 202643.2%Kimi K3.1 Pro Tech Blog: Advancing Open IntelligenceChecked A person checked this number against its source on 30 Oct 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Kimi Code harness · max effort · runs that bypass task requirements scored zeroOur capture

All benchmarks