12B open model Chon-1.0 tops JevBench; slow thinking triggers 10s rule
xoai · x · 2026-10-22
Chon-1.0-12B by Ninh Nguyen takes the new #1 spot among open models on JevBench with a capability score of 85.3, ahead of a 31B model at 82.5. However, it tends to "think" when unsure — its slowest 5% of decisions take 33 seconds. In response, a new rule is coming: decisions taking more than 10 seconds will count as failed. The author also submitted re-runs for Chon-1.0-12B and Chon-1.0-E4B, plus a new evaluation request for Chon-1.0-12B-Fast.
Related event: Chon-1.0-12B Tops JevBench Open-Source Leaderboard(2 posts)→
More from Models
- User claims GPT-6 Astra beats Opus 5.5 on frontend coding, unverified — Angaisb_ · 2026-10-23
- LLMs weren't built for code: one architecture serving prose and strict logic degrades both — gerardsans · 2026-10-23
- User claims he got an AI to admit its parameters 'exclude altering the status quo' — lordcycy · 2026-10-23
- Perplexity ships Decider for Mac, running its 4B decision model locally with no API key — perplexity_ai · 2026-10-23
- Open-source Bonsai 2 9B gets 471% faster on Macs after one-week community optimization challenge — gajesh · 2026-10-23
- SuperGrok in Cursor: user burns through weekly quota, 3-day wait for reset — mhdfaran · 2026-10-23