Event ·Multi-source

Artificial Analysis 上线 VIALS-AA:生命科学视觉推理榜单

Artificial Analysis 联合 Handshake AI 推出 VIALS-AA 榜单,评测模型在生命科学视觉推理上的能力。VIALS 基准包含 161 个任务,覆盖凝胶印迹、流式细胞图、质粒图谱、系统发生树等 8 个领域,用开源 harness Stirrup 跑 3 次取 pass^3。结果 Gemini 4 Carbon(high)以 64% 居首,GPT-6 Astra(max)63%、Claude Opus 5.5 61%。成本差距明显:Opus 5.5 每任务 1.64 美元,约为 GPT-6.1 Sol(0.056 美元)的 29 倍,原因是平均 27 轮对 8 轮。开源模型方面 Kimi K3.1 Pro 以 45% 领先,MiMo-V2.6-Pro 43%。

Current read

161 个任务专考读凝胶图和质粒图这些科研视觉推理,Gemini 4 Carbon 险胜 GPT-6,但 Claude 每任务贵 29 倍,选模型前先看这份榜单。

11 sources63° AI heatLast updated 2026/11/6 17:09:35

Evidence

11 sources
Primary sourceArtificial Analysis
View source
Related source 1lmarena.ai
View source
Related source 2rohanpaul_ai
View source
Related source 3shao__meng
View source
Related source 6Gorden Sun
View source
Related source 7@koltregaskes
View source
Related source 8TestingCatalog
View source
Related source 10kimmonismus
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

VIALS-AA leaderboard ranks models on life science visual reasoning · 事件专题 | AITOP