Nace ships Drex Max 1.1 decision model, Decision Index up to 70.8 at 172 ms

omarsar0 · x · 2026-10-28

Nace released Drex Max 1.1, its decision model with significantly improved out-of-distribution generalization.

• Key numbers: Decision Index 70.8 (up from 67.6), 172 ms median latency
• Specs: multimodal, 262K context window, launch price $0.03/1M input tokens (50% discount)
• The benchmark chart shows it leading decision benchmarks (Decision Bench 94.2, DecideBench 99.0) and beating GPT-6 Sol and Claude Opus 5.5 on OSWorld-Verified automation (0.787), at $0.06 per 1K decisions vs $3.33–$10.17 for frontier LLMs
• Targeted at messy-document work: invoice splitting, statement enrichment, transactional judgment

Elvis Omarsar has been testing it on research tasks and is curious about the better generalization.

Original post →

More from Models

• ARC Prize finds v2 = v1^4.53 power curve explains 98% of ARC-AGI-2 score variance — GregKamradt · 2026-10-29
• Paper: Max reasoning effort costs up to 42x more and often fails tasks lower effort solves — zainhas · 2026-10-29
• Don't get hyped: today's OpenAI news may just be Pro 200 limits not getting cut — Angaisb_ · 2026-10-29
• Cryptographer points abliterated GLM at Telegram's secret-chat crypto — and it 'killed itself' — matthew_d_green · 2026-10-29
• Top reasoning effort costs up to 42x more on tasks low effort already solves — zainhas · 2026-10-29
• RealityBench: 35 VLMs tested on physical work understanding, measuring stays a weak spot — arnabdotorg · 2026-10-28

Models channel →