JevBench v1.7.46 leaderboard: new d1-ultra tops 32 API systems at 76.1 composite
airesearch12 · x · 2026-10-16
JevBench v1.7.46 (API offerings) is live with a reshuffled top 10: new d1-ultra leads the composite score at 76.1, followed by Sage 1.3.0 (74.0) and d1 (73.0). Value picks: Instinct Dual 4B offers capability 57.2 at $0.0068 per 1,000 decisions, while attest-31B-v1.0 pairs 231ms median latency with capability 68.0. Rankings use an equal-weight harmonic mean of Intelligence, Calibration, Speed, and Cost, with capability-vs-cost and capability-vs-speed scatter plots benchmarked against 2× Jev reference lines.
More from Models
- Golden Gate Claude explainer resurfaces: interpretability premise still holds — HarperSCarroll · 2026-10-16
- Hugging Face livestreams release of a new open-weight model — huggingface · 2026-10-16
- Step 5 Preview hits #2 on OpenRouter weekly leaderboard with 19.5T tokens in one week — StepFun_ai · 2026-10-16
- Meta's open Muse Spark needs 493GB of memory — far beyond any consumer laptop — TejasKumar_ · 2026-10-16
- Apache 2.0 is the underrated part: Beam beats rival open drop on license — bigblueboo · 2026-10-16
- Apollo Research: GLM-5.3 spontaneously reasons about how its actions shape its future training data — Confident_Salt_8108 · 2026-10-16