Artificial Analysis Launches VIALS-AA Leaderboard for Life Sciences Visual Reasoning

1 reports 1 reporting sources Updated 3 hours ago

Understand the event

AI overview

Artificial Analysis launched VIALS-AA, a leaderboard for Handshake AI’s VIALS benchmark, which tests visual reasoning across 161 tasks in eight life sciences and biotech domains. Gemini 4 Carbon (high) leads with 64%, followed by GPT-6 Astra (max) at 63% and Claude Opus 5.5 (max with fallback) at 61%. Models run each task three times in the Stirrup agent harness. GPT-6 Luna (medium) grades the answers, and the leaderboard reports the share of tasks judged correct in all three runs.

Generated by AI from reports · Updated 52 minutes ago

Latest development11/7 01:09 (UTC+8)

Artificial Analysis Launches a VIALS Leaderboard for Life Sciences Visual Reasoning Artificial Analysis · X

Models in this story

GPT-6 Astra#3 overall$10 input / $50 output per million tokens
Claude Opus 5.5#1 overall$4 input / $20 output per million tokens
GPT-6 Luna$0.1 input / $0.5 output per million tokens

Compare their API prices API prices of all models

Report timeline

Follow the reports to explore different sides of the event.

11/7

01:09
Artificial Analysis · X
Artificial Analysis Launches a VIALS Leaderboard for Life Sciences Visual Reasoning
Artificial Analysis is launching VIALS-AA, a leaderboard for Handshake AI’s VIALS benchmark, which tests visual reasoning across 161 tasks in eight life sciences and biotech domains. Models run each task three times in the Stirrup agent harness, and GPT-6 Luna (medium) grades answers; the leaderboard reports the share judged correct in all three runs. Gemini 4 Carbon (high) leads at 64%, followed by GPT-6 Astra (max) at 63% and Claude Opus 5.5 (max with fallback) at 61%.

Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue

Event heat trend

There is not enough continuous observation data to plot a trend yet.