Benchmarks Jev on chess moves and identifying which game NPC a player addresses.
Real data. Real impact.
Emerging
Developers
git clone https://github.com/wondertwins/jev-benchmark.gitPer week
Excellent
One command unlocks capabilities that would take hours to build.
Benchmarks Jev on chess moves and identifying which game NPC a player addresses.
Selects legal chess moves or judges whether an utterance addresses each NPC.
Publishes labeled data, raw requests and responses, and evaluation code.
Chess strength, F1 and latency come from the author’s specific tasks and settings, not general game-playing capability. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
Jev is TypeSafe AI's System One decision model: it returns typed scores and choices (not free text), so agents can route, filter and gate at low latency and cost.
Source: wondertwins/jev-benchmark — 6 stars, MIT. Listed by Awesome Jev.
MIT
4,600+ AI skills, agents & workflows. Install in 60 seconds. Part of the Torly.ai family.
© 2026 Torly.ai. All rights reserved.