TargetBench (Insilico)

10 disease-area target identification benchmarks on ScienceAIBench/DDB (cancer, cardiovascular, endocrine/metabolic, fibrotic, inflammation/immunology, neuro, etc.).

Composite

84.6

Experimental validation

Wet-lab confirmed

Stages

Target IDDisease Modeling

Modalities

cross-modality

Task types

target-prioritization

Size

benchmarks: 10
disease_areas: 10

License

CC-BY

First release

2025-03

Last updated

2026-04

Official site

→ project page

Leaderboard

→ leaderboard

Dataset

→ dataset

Code / GitHub

→ repository

HuggingFace

→ HF

Paper

TargetBench methodology · I, n, s, i, l, i, c, o, , A, I, , T, e, a, m · 2025 · paper · doi:N/A — portal · 5 citations

Flags

none

Experts

Alex Zhavoronkov, Alex Aliper

Groups

Insilico Medicine

Hosted by

ScienceAIBench, Drug Discovery Benchmarks (DDB)

Related benchmarks

Open Targets Platform, DepMap (Cancer Dependency Map)

Rubric (7-criterion)

rigor

coverage

maintenance

adoption

quality

accessibility

industry_relevance

Notes

Disease-organized target ID benchmark — unique axis. Frontier LLM leaderboard.

← Back to all benchmarks

Compare:

Open comparison →