Atlas

Benchmarks

← All benchmarks

VIALS

Multimodal · 2026-08-21

Handshake AI's VIALS (Visual Interpretation of Artifacts in the Life Sciences) is a visual question-answering benchmark of 161 expert-written tasks on artifacts from biotech and pharmaceutical R&D: gels and blots, phylogenetic trees, flow-cytometry plots, plasmid maps, cell-counting images, protein-structure and binding views, and small-molecule structures. Models see only the image(s) and question at their provider's default inference settings, and a GPT-5-mini judge decides whether the final answer matches the held-out ground truth (or falls in an accepted numeric range). Accuracy is averaged over three rollouts per task; failed or refused requests count as incorrect.

Top models (higher is better)

ModelScore
GPT-6 Astra49.9
GPT-6.1 Sol49.1
Gemini 4 Argon47.2
Claude Sonnet 5.541.0
Claude Opus 5.540.2
Muse Wonder31.5
Gemini 3.8 Flash29.4
Gemini 3.7 Flash26.5
GPT-5.6 Sol26.5
Claude Opus 524.4
Muse Spark 1.222.6
Gemini 3.1 Pro Preview21.5
Kimi K320.9
Grok 4.620.5
Grok 4.718.2
DeepSeek V4.1 Flash12.6
GLM-4.6V10.8
MiniMax M310.8
Mistral Medium 3.57.9
Loading Atlas data…