Frontier Log

Benchmark · Active

HLE-Diamond

Created by Center for AI Safety and Scale AI, 22 Sep 2026 · Higher is better · Website

01020304050Oct 202639.4%Kimi K3.1 Pro01020304050Oct 202639.4%Kimi K3.1 Pro

Settings and run setups

Task setToolsHarnessProviders
HLE-Diamond (1,000 questions)No toolsNot statedGoogleThinking Machines
HLE-Diamond (1,000 questions)Not statedNot statedMoonshot AI

Download image

Results

ModelScoreSource
Kimi K3.1 Pro24 Oct 202639.4%Kimi K3.1 Pro Tech Blog: Advancing Open Intelligencemax reasoning effort · full 1,000-question setOur capture

All benchmarks