Evaluator Bench
Evaluator Bench is (research preview). It is ranked #254 on the AI Radar, in AI infra & evals, first seen 3 days ago and shared in 2 posts (17.5k views).
What Evaluator Bench says about itself
Third-party evaluators of frontier AI, scored on six dimensions of structural independence plus two evaluation conditions. Every score traces to a signal and a source, under an evidence policy you choose.
Evaluator Bench — the AI evaluator independence ledger Evaluator Bench Preview of the first release. Everything here is one batch of initial research, and every score is provisional until 2026-10-15 . Organizations and people named here, and anyone else, can submit corrections or evidence until then; what arrives becomes the launch round of the paper. No tag is citable until the gates pass. How to submit . Update, 15 September: the re-derivation pass did not move values; earlier v0.1 rules and scope decisions did. Evidence current to 15 Sep 2026 Independence only. Not quality, coverage, or competence. Independence, scored. An open ledger of…
What people said about Evaluator Bench on X
the independence of AI evaluators is going to matter more... so i made it a "benchmark": http://evaluatorbench.com (research preview) source-linked directory of third-party evaluators of frontier AI. each one has an independence score you can take apart: change the weights, change which evidence counts (standard,…
— @yoheinakajima, 3 days ago · 62 likes · see the post
the design of http://evaluatorbench.com grew out of a summer project, http://epistemedia.org (which i still need to write about), and runs on @activegraphai the pattern across all three projects is that it treats the journey as the primary substrate, and the destination as a projection of it
— @yoheinakajima, 3 days ago · 36 likes · see the post
Alternatives to Evaluator Bench
- Ling-3.0-flash-Fin — 🚀 ZDTaichu5.0-9B is now on ModelScope! 🤖
- classifier.dev — now outperforms jev and is free
- Jev API, Pricing & Playground — Jev is now available on the @vercel AI Gateway
- Darkbloom — Private AI inference through hardware-attested Apple Silicon providers. Your prompts stay encrypted, your data stays…
- glm-5.3-flash-exl3-2x-dgx-sparks — GLM-5.3 Flash EXL3 for 2-4x DGX Sparks. Contribute to MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks development by…
- Intelligence Benchmarking — Detailed intelligence benchmarking methodology for LLM quality evaluations.
Evaluator Bench in numbers
- Rank on the AI Radar: #254 of 1192
- Shared in 2 posts by 1 account: @yoheinakajima
- 17.5k views on those posts
- First seen 3 days ago, last shared 3 days ago
- Pricing seen by Jev: not stated
- Market: AI infra & evals
FAQ
What is Evaluator Bench?
(research preview) It was first shared on X 3 days ago and is ranked #254 on the AI Radar.
Is Evaluator Bench free?
Pricing is not stated on the page we read.
Who shared Evaluator Bench?
1 account on X, including @yoheinakajima, in 2 posts totalling 17.5k views.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 27.2k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:40 UTC. Full method.