AI Radar
Support
LiveUpdated 2026-09-19 18:08 UTC

AEON Bench

AEON Bench — AEON score 91.9 overall · max ctx 256K · peak 238 tok/s concurrent · attested

AEON Bench is AEON score 91.9 overall · max ctx 256K · peak 238 tok/s concurrent · attested. It is ranked #544 on the AI Radar, in Open & local models, first seen 7 days ago and shared in 2 posts (15.4k views).

Visit aeon-bench.com

What people said about AEON Bench on X

This benchmark just came in and it blew my expectations out of the water! This is for the NVFP4 Mixed quant running on a SINGLE DGX SPARK! Best score of all models of all time on Aeon Bench, beating DeepSeek v4 and GLM5.2 and of course even stock Qwen3.8-27B!…

@SpaceTimeViking, 7 days ago · 139 likes · see the post

If you dig into the performance stats you see SINGLE STREAM getting 70 tokens per second in the Coding Category. Sweet spot for concurrency looks like c10 with only marginal gains moving to c16 Recipe to replicate is on the performance section for the Qwen3.8-27B Aeon Ult.

@SpaceTimeViking, 7 days ago · 24 likes · see the post

Alternatives to AEON Bench

AEON Bench in numbers

FAQ

What is AEON Bench?

AEON score 91.9 overall · max ctx 256K · peak 238 tok/s concurrent · attested It was first shared on X 7 days ago and is ranked #544 on the AI Radar.

Is AEON Bench free?

Pricing is not stated on the page we read.

Who shared AEON Bench?

1 account on X, including @SpaceTimeViking, in 2 posts totalling 15.4k 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 18:08 UTC. Full method.