ARC-AGI-2

Tools & Infrastructure

Frontier benchmark for measuring general intelligence capabilities in AI agents beyond pattern matching

🌐 Visit website ↗

🔗 Similar tools

GAIA Benchmark

Benchmark for General AI Assistants measuring real-world reasoning and tool use
JetBrains Kotlin Benchmark

JetBrains Kotlin Benchmark is a public benchmark from JetBrains that evaluates AI coding a…
τ²-bench (tau2-bench) v1.0.1 ★ 2.0k

τ²-bench v1.0.1 is Sierra Research's benchmark for evaluating tool-agent-user interaction …
PerspectiveGap ★ 3

PerspectiveGap (arXiv 2606.08878) is the first benchmark for multi-agent orchestration pro…
AIME 2025 / Humanity's Last Exam (HLE)

AIME 2025 / Humanity's Last Exam (HLE) is a benchmark for evaluating AI on elite-level mat…
MiniMax M3

MiniMax M3 is an open-weight flagship model released June 1, 2026, using MiniMax Sparse At…