JevBench maintainer: 4B model won on speed and cost, not intelligence
airesearch12 · x · 2026-09-25
Explaining decider-4b v2's JevBench win, the maintainer notes Jev still leads on intelligence (53.1 vs 49.4) and calibration; the 4B model won via 5x speed and roughly half the cost, since JevBench weights intelligence, calibration, speed and cost equally. Users seeking raw intelligence can sort by the intelligence column.
Related event: Open-source 4B model tops JevBench on speed and cost, not intelligence(3 posts)→
More from Models
- DeepMind launches AlphaGenome 2, spotting nearly 2x more gene-regulating mutations — GoogleDeepMind · 2026-11-11
- Gemini 4 Carbon matches predecessor's score but explores less, gets distracted — patience_cave · 2026-11-11
- Fable 5.2 takes MazeBench frontier, matches GPT-6 Astra puzzle-solving — patience_cave · 2026-11-11
- MazeBench: Fable 5.2 scores 15%, near-frontier at half price; Gemini 4 Carbon 11% — patience_cave · 2026-11-11
- ERNIE 5.5 Flash Preview enters LMArena Battle Mode for crowdsourced ranking — arena · 2026-11-11
- Blind tests: DeepSeek matches Opus on 95% of agentic loops at 40x lower cost — bindureddy · 2026-11-11