The TRACES Leaderboard
The TRACES Leaderboard is Live leaderboard. It is ranked #118 on the AI Radar, in AI infra & evals, first seen 10 days ago and shared in 5 posts (1.4M views).
What The TRACES Leaderboard says about itself
TRACES is a new evaluation paradigm for Discoverative AI — built not to measure how well AI answers known questions, but how far it can push the frontier of the unknown.
What people said about The TRACES Leaderboard on X
A generational leap, but not on every dimension. Yesterday we put the TRACES board up. Here is the first comparison worth pulling out of it. GPT-6-astra @OpenAI tops the board but that is not the interesting part. Against GPT-5.6-sol, same harness, 140 agent episodes, it gains on all six capabilities. The gains are…
— @Apodex_AI, 8 days ago · 780 likes · see the post
GPT-6 Astra @OpenAI is here. Everyone's asking how smart it is. We asked a different question: can it discover the unknown? We ran it through TRACES — our benchmark for scientific discovery capability. Six process dimensions, not one score. Result: it tops our leaderboard. Real generational jump — Evidence and…
— @Apodex_AI, 10 days ago · 317 likes · see the post
Most AI benchmarks test retrieval: can a model find an answer we already know? But science’s hardest problems demand discovery: can a system earn an answer no one knows yet? Meet TRACES 🧭—the world’s first benchmark for discoverative AI: systems that can weigh evidence, test hypotheses, and reach verifiable…
— @Apodex_AI, 3 days ago · 71 likes · see the post
Alternatives to The TRACES Leaderboard
- 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.
The TRACES Leaderboard in numbers
- Rank on the AI Radar: #118 of 1183
- Shared in 5 posts by 2 accounts: @Apodex_AI, @DataChaz
- 1.4M views on those posts
- First seen 10 days ago, last shared 2 days ago
- Pricing seen by Jev: not stated
- Market: AI infra & evals
FAQ
What is The TRACES Leaderboard?
Live leaderboard It was first shared on X 10 days ago and is ranked #118 on the AI Radar.
Is The TRACES Leaderboard free?
Pricing is not stated on the page we read.
Who shared The TRACES Leaderboard?
2 accounts on X, including @Apodex_AI, @DataChaz, in 5 posts totalling 1.4M 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. 27.1k 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 17:00 UTC. Full method.