Today for AI
HOT RADAR
llmHEAT 27.3°

AI CURATED HOT STORY · 11/7/2026

Artificial Analysis Launches VIALS-AA Visual Reasoning Leaderboard, Gemini 4 Leads

1 reports archived1 independent sourcesupdated 11/7/2026, 01:09:35
Synthesis & Latest Updates
1 Sources Cross-Validated

Artificial Analysis launched VIALS-AA, a leaderboard built on Handshake AI's VIALS benchmark, evaluating frontier models on 161 life-science visual reasoning tasks. Gemini 4 Carbon leads narrowly at 64% pass^3, followed by GPT-6 Astra at 63% and Claude Opus 5.5 at 61%, a 3-point spread. Refusals on several tasks show scientific artifact interpretation remains a clear weakness for frontier models.

LATEST/Artificial Analysis launched VIALS-AA, a leaderboard built on Handshake AI's VIALS benchmark, evaluating frontier models on 161 life-science visual reasoning tasks. Gemini 4 Carbon leads narrowly at 64% pass^3, followed by GPT-6 Astra at 63% and Claude Opus 5.5 at 61%, a 3-point spread. Refusals on several tasks show scientific artifact interpretation remains a clear weakness for frontier models.

Hourly heat curve

2 fully observed hours
Fewer than 3 fully observed hours; trend not plotted yet.

Coverage timeline

Total 1 reports · Latest first
  1. Artificial Analysis (@ArtificialAnlys)T1·72 pts

    Artificial Analysis Launches VIALS-AA Visual Reasoning Leaderboard, Gemini 4 Leads

    • VIALS-AA spans 161 tasks across 8 domains, covering gel blots, flow cytometry plots, plasmid maps and phylogenies
    • Top three are within 3 points: Gemini 4 Carbon 64%, GPT-6 Astra 63%, Claude Opus 5.5 61%
    • Tasks run in the open-source agent harness Stirrup, repeated three times and scored as pass^3
    • Multiple models refused on some tasks, showing scientific artifact interpretation remains a clear gap