AI Radar
Support
LiveUpdated 2026-11-06 15:10 UTC

ExplorationBench

ExplorationBench — 🌐 Website & leaderboard

ExplorationBench is 🌐 Website & leaderboard. It is ranked #1787 on the AI Radar, in Frontier models, first seen 37 days ago and shared in 5 posts (97.3k views).

Visit explorationbench.com

What ExplorationBench says about itself

A benchmark for exploration in verifiable Alien Worlds: executable rules that conflict with familiar knowledge, so they have to be found by probing rather than recalled.

ExplorationBench · Measuring AI Systems' Exploration in Verifiable Alien Worlds Sections Sections Close Read the paper Read the blog Fudan University · Hunyuan Team, Tencent · Tsinghua University ExplorationBench Can AI systems acquire unfamiliar rules through exploration? We test them in verifiable Alien Worlds, whose rules are executable and conflict with familiar knowledge. Read the paper Read the blog GitHub Leaderboard → 0 alien worlds 0 discovery targets 0 held-out tasks 0 frontier systems Leaderboard Held-out accuracy under autonomous exploration. Three independent trajectories per system and sandbox, ranked by Best@3, the…

Alternatives to ExplorationBench

ExplorationBench in numbers

FAQ

What is ExplorationBench?

🌐 Website & leaderboard It was first shared on X 37 days ago and is ranked #1787 on the AI Radar.

Is ExplorationBench free?

Pricing is not stated on the page we read.

Who shared ExplorationBench?

3 accounts on X, including @TencentAI_News, in 5 posts totalling 97.3k views.

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 15:10 UTC. Full method.