REAX 1.3 from four-week-old Bittensor subnet claims #1 on Hugging Face Decision Index
airesearch12 · x · 2026-11-06
Decision Models says REAX 1.3, built with miners on Bittensor Subnet 92 just four weeks after launch, is #1 on the Hugging Face Decision Index 0.4.1; mammoth-1 (served as s1-pro-5) leads the public-weights ranking.
- The team also runs a "Jev-compatible" decision API for routing/approval/scoring tasks, outputting per-option probabilities, with EU hosting available
- Self-measured results: mammoth-1 scores 10.2 points above Jev 1.14.0 on the same items; s1-pro-3 hits 2.6x reference server throughput via vLLM-SR at roughly half Jev's price
- Caveat: the JevBench leaderboard is run by Decision Models' own founder, so the benchmark's independence is questionable
Related event: Bittensor subnet ships REAX 1.3, tops HF Decision Index in four weeks(6 posts)→
More from Models
- From "can't write coherent text" to complaining a 2B model can't run a training pipeline in 10 minutes — cephaloform · 2026-11-07
- Rubricon: scaling test-time compute to auto-generate expert-grade LLM rubrics — deliprao · 2026-11-07
- Kimi K3.1 Pro lands on Microsoft Foundry with 1M-token context for agentic work — DanWahlin · 2026-11-07
- Ripple 65B Preview vs Qwen 3.8 coding benchmarks: 79.1 on SWE-Bench Pro — Nota_ReAlperson · 2026-11-07
- Fireship: OpenAI's unnamed model just cracked 3-SAT, threatening a 27-year-old hypothesis — Fireship · 2026-11-07
- Bittensor subnet model tops respected independent leaderboard just ~30 days after launch — airesearch12 · 2026-11-07