Step 5 Preview detailed breakdown: strong reasoning, weak agentic scores
ArtificialAnlys · x · 2026-09-22
Artificial Analysis shared the full per-evaluation breakdown for Step 5 Preview: agentic work is its clear weakness — GDPval-AA 1,566 Elo, AA-Briefcase 1,432 Elo, and Terminal-Bench 4.0 at 33%, all behind GLM-5.3 (max) and Qwen3.8 Max. Knowledge and reasoning show the reverse: it leads both on HLE (46%), CritPt (21%), and the AA-Omniscience Index (16).
Related event: Artificial Analysis Reviews Step 5 Preview: 44 Points at 1/2.8 the Cost(6 posts)→
More from Models
- OpenAI to retire Standard Voice mode, offering crisis support to affected users — shaunralston · 2026-11-12
- OpenAI Retires ChatGPT's Standard Voice Mode, Offers Users Crisis Support — shaunralston · 2026-11-12
- Grok Bot 1.0 Announced: Shareable Bots With Upgraded Collaboration — SpaceXSI · 2026-11-12
- Gemini Decision 1 Benchmarks Leak: Leads Most Evals With 0.025 ECE — Angaisb_ · 2026-11-12
- Polymarket odds put Chinese AI lab at #1 by year-end at just 6% — Polymarket · 2026-11-12
- FutureHouse's deslopper trains Kosmos to write indistinguishably from human experts — proteinrosh · 2026-11-12