VIALS-AA leaderboard goes live: compare models on score, cost and tool calls
ArtificialAnlys · x · 2026-11-12
Artificial Analysis launched an interactive leaderboard for VIALS-AA (with tools), letting users compare models on score, per-task cost and tool call counts.
The benchmark, based on Handshake AI's VIALS, spans 161 tasks across 8 scientific artifact domains (blots, microscopy, flow cytometry, plasmid maps, phylogenetic trees). Models run as agents with sandboxed Python and an image-viewing tool, three repeats per task, scored via pass^3. The underlying paper is on arXiv.
More from Models
- Fable 5.2 cuts refusals dramatically but slides to 40th & 53rd on BullshitBench — burny_tech · 2026-11-12
- Artificial Analysis: Upgrading Claude model tier beats maxing reasoning effort on cost — ArtificialAnlys · 2026-11-12
- Google Showcases Gemini 4 Carbon: Building a Custom CUDA/C++ VFX Engine From Scratch — burny_tech · 2026-11-12
- Claude iOS spotted adding 'Saved logins' for signing into websites, fueling Duet speculation — testingcatalog · 2026-11-12
- Fable 5.2 reverse-engineers how 1400s composers wrote four-voice counterpoint, then composes — imjustnewatai · 2026-11-12
- GPT-Live talk at VapiCon: OpenAI pushes natural speech with frontier intelligence — juberti · 2026-11-12