JevBench v1.4 - now >70 models!
This is a dev post classified by Jev as AI dev tools (a launch), kept by the Dev Radar because it carries real work, not commentary.
JevBench v1.4 - now >70 models! Top 5: 1⃣ Jev 👑 2⃣ JevK5 3⃣ Hopper 4⃣ Winnow-12B Q8 5⃣ reflex 4B Thanks to everyone who submitted a system and challenged the method - with v1.4 the methodology has improved quite a bit (see below). https://benchmarkheaven.com/jev-models
Posted by Florian S (6.1k followers) 55 min ago · 5 likes · 276 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- Recraft V4.1 Flash by @recraftai is now live on fal. — @fal
- GPT 6 Sol and Luna are now available in the Warp Terminal and the Warp Agent CLI — @warpdotdev
- 📦 New JS package just dropped: huggingface/lerobot — @julien_c
- Oct 4, San Francisco — @neondatabase
- Grok 4.7 takes a step forward over Grok 4.6 in Artificial Analysis’s benchmarks: — @merge_api
- Claude gave out a banked reset yesterday. If you want your usage to last longer this… — @Voxyz_ai
- Excited for next Tuesday, Sept 29, and our monthly @daytonaio AI Builders Demo Night in… — @daytonaio
- Claude Opus 5.5 built a 300 metre tall flower that blooms in real time. — @pankajkumar_dev
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. 22.6k posts from 5k X accounts over the last 21 days, 2.6k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 15:21 UTC. Full method.