4B open model tops JevBench by being 5x faster and half the price
airesearch12 · x · 2026-09-25
JevBench v1.4.2 has a new #1: the open 4B model decider-4b v2, beating Jev 1.13.0, JevK5, Cygnet and Hopper. Jev still leads on intelligence (53.1 vs 49.4) and calibration, but decider-4b wins on speed (5x faster) and cost (half the price); the benchmark weights smart, calibrated, fast and cheap equally.
Related event: Open-source 4B model tops JevBench on speed and cost, not intelligence(3 posts)→
More from Models
- Micius-Flash: 27B Multimodal Model for Hardware and Semiconductor Agents — zhiman-ai · 2026-11-11
- Claude IP risk-check site goes viral as users audit their IPs ahead of new rules — vista8 · 2026-11-11
- Baidu says RSI auto-optimized ERNIE inference, 6.24x decode speedup on Kunxin P800 — xiaohu · 2026-11-11
- Baidu's ECHO: multi-token prediction reusing the last layer as a drafter — xiaohu · 2026-11-11
- ERNIE 5.5 Flash Preview: 280B-param multi-router MoE activating only 14B per token — xiaohu · 2026-11-11
- ERNIE 5.5 recreates the Pelican test: 117-second animation drawn frame-by-frame in Python — xiaohu · 2026-11-11