RSI-Exam
RSI-Exam is RSI-Exam evaluates whether an AI agent can improve a working method and generalize to unseen data. 88 active tasks across 6 domains: 35 public and 53 private.. It is ranked #4680 on the AI Radar, in Frontier models, first seen 11 days ago and shared in 1 post (5.2k views).
RSI-Exam · Benchmarking Recursive Self-Improvement through Executable Research RSI-Exam RSI-Exam : Benchmarking Recursive Self-Improvement through Executable Research It evaluates whether an AI agent can improve itself over a long horizon and generalize to unseen data. Hours of autonomous experimentation on the method that solves the task or the harness that drives a frozen model, then one final run on a hidden test set. Browse tasks Leaderboard How it works Contribute a task RSI-Exam 0.1 Leaderboard Full 88 Public 35 Private 53 Model resource comparison Average spend Average run time Average output tokens Mean hidden-set score over the 88…
What people said about RSI-Exam on X
Grok 4.7 on RSI Exam does as well as Kimi K3 (original) now let's see how the latest models do
— @teortaxesTex, 11 days ago · 54 likes · see the post
Alternatives to RSI-Exam
- Thinking Machines Lab — Mantic have been using Tinker since it launched. This guest post is a technical deep dive on what they have built so…
- openai.com —
- Tencent Hy — Tencent Hy
- clocktowerbench.com — You can see the full benchmark at the website, and I’ve also made it so that you and your friends can play again the AIs
- Claude — Basecamp for Claude is live!
- Mercor — Evaluate frontier AI models with Mercor's APEX AI Benchmarks & Leaderboards. Measure AI productivity across software…
RSI-Exam in numbers
- Rank on the AI Radar: #4680 of 10402
- Shared in 1 post by 1 account: @teortaxesTex
- 5.2k views on those posts
- First seen 11 days ago, last shared 11 days ago
- Pricing seen by AGK Intelligence: not stated
- Market: Frontier models
FAQ
What is RSI-Exam?
RSI-Exam evaluates whether an AI agent can improve a working method and generalize to unseen data. 88 active tasks across 6 domains: 35 public and 53 private. It was first shared on X 11 days ago and is ranked #4680 on the AI Radar.
Is RSI-Exam free?
Pricing is not stated on the page we read.
Who shared RSI-Exam?
1 account on X, including @teortaxesTex, in 1 post totalling 5.2k 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.