JevBench v1.2: open-source LLM leaderboard weighting intelligence, calibration, speed, cost
airesearch12 · x · 2026-09-21
Benchmark Heaven launched JevBench v1.2, an open-source leaderboard for "Jev-class" decision models. The main score is a geometric mean of intelligence, calibration, speed and cost, each weighted 25%. It offers alternative rankings emphasizing any single dimension, lets users re-configure weights for custom rankings, and supports filtering by hosting region, data confidentiality policies, open weights and price bases — released in response to criticism that prior comparison methodology was unclear.
Related event: JevBench: Open-Source Benchmark for Typed Decision Models(3 posts)→
More from Models
- Datalab claims parsing accuracy second only to Gemini at 1/37 the cost and 6x speed — VikParuchuri · 2026-11-12
- Datalab fast-mode OCR beats Opus 5.5 and GPT-6.1 Sol at 1/4 to 1/68 the price — VikParuchuri · 2026-11-12
- Claude's world knowledge impresses: model guesses user identity from one prompt — adonis_singh · 2026-11-12
- Gemini 4 Carbon opens to all at $2/$10, price doubling to $4/$20 on Dec 1 — socialwithaayan · 2026-11-12
- Ten wild Gemini 4 Carbon demos in 24 hours: CUDA meadows, V8 engines, mech stomps — socialwithaayan · 2026-11-12
- How to cut Fable 5.2 token costs by 90%: Arc routing plus a lean CLAUDE.md — EXM7777 · 2026-11-12