Artificial Analysis rolls out Intelligence Index v4.3 with private AutomationBench-AA
inductionheads · x · 2026-09-08
Artificial Analysis announced Intelligence Index v4.3, an intermediate step toward v5: Terminal-Bench is upgraded from 2.1 to 4.0, and τ³-Banking is replaced by AutomationBench-AA, an agentic workflow automation benchmark based on Zapier's benchmark with a private test set. Each v4.2/v4.3 change is said to stand on its own merits.
Related event: Artificial Analysis Intelligence Index Updated to v4.3(4 posts)→
More from Models
- User: GPT 6 Astra is great but full of misleading jargon and weird naming — zsakib_ · 2026-09-08
- GLM 5.3 Is Currently Free via TokenRouter, Works With Your Favorite AI Agents — Roger_M_Taylor · 2026-09-08
- GPT-6 Astra hands-on: solves Blender, trained on 100k GPUs, compute still the bottleneck — thedealdirector · 2026-09-08
- Will Depue: 'There Is No Such Thing as a World Model, Only Autoregressive Video Models and Mistakes' — willdepue · 2026-09-08
- Does Owning Multiple ChatGPT Pro 20x Accounts Violate OpenAI's TOS? — BingBongDingDong222 · 2026-09-08
- Heavy user burns 12% of ChatGPT quota in 2 hours, mulls buying a second account — BLUECOW009 · 2026-09-08