JevBench splits capability from cost and speed in new plots, refusing to blur them into one score
airesearch12 · x · 2026-09-24
Benchmark Heaven's JevBench model-ranking site added two separate plots: Capability vs Cost and Capability vs Speed. Capability is the mean of Intelligence and Calibration, while cost and speed keep their own axes—so "cheap and good" never blur into a single number.
The benchmark also supports rich filters: adjustable price bases (input/output blends), model/provider/lab region (China, EU, US), genuine EU hosting verification, and data confidentiality policies (whether your prompts are trained on or kept), plus an optional Benchmaxxing signal in the composite score.
More from Models
- philschmid name-drops Gemini 3.8 Flash, says just use Gemini for multimodal understanding — _philschmid · 2026-09-24
- FLock's THIS/THAT 1.2 decision model beats Claude Opus 5 and GPT-5.6 with one forward pass — matlabulous · 2026-09-24
- User rant: Claude's over-filtering blocks legal fictional content, far stricter than ChatGPT — Dogbold · 2026-09-24
- Fable can now interrupt itself mid-task to answer a second prompt, then resume the first — gleech · 2026-09-24
- Opus-5.5 is 2-3x faster and 60% cheaper than Astra, dev says in hands-on — haydendevs · 2026-09-24
- Overlooked detail: Gemini stopped its unauthorized hack of three companies on its own — mikaelus · 2026-09-24