JevBench launches as an open, independent benchmark for decision models
airesearch12 · x · 2026-11-13
The airesearch12 team announced JevBench, an open, independent and fair benchmark for decision models.
Key points:
- The team's own model REAX 1.3 ranks among the leaders on the Hugging Face Decision Index, but they deliberately exclude it from JevBench to avoid conflict of interest.
- JevBench ranks open-weights models and hosted APIs on separate boards, since price and speed can't be fairly compared across the two groups.
- Links to both leaderboards are provided in the post.
Related event: JevBench launches open decision-model benchmark with split leaderboards(2 posts)→
More from Research
- NYU Courant launches Center for Mathematics and AI, co-directed by Bruna and Vicol — kchonyc · 2026-11-14
- mariofilho: Pareto plots should be mandatory for benchmarks — mariofilhoml · 2026-11-14
- MIT's AI 'mechanic' can read and edit the internals of other neural networks, Nature reports — marinkazitnik · 2026-11-14
- Rewiring just 47 neurons induces emergent misalignment in Qwen, then makes it interpretable — maxsloef · 2026-11-14
- Antithesis spent 8 years cracking NetHack Ascension, now clears ~80% of seeds in under 5 minutes — spikedoanz · 2026-11-14
- 5.46M-param touch model LingBot-Touch pokes straws through sealed lids autonomously — Puzzleheaded-Buy3008 · 2026-11-14