LatchBio Capabilities v1.0
Progress Over Time
Interactive timeline showing model performance evolution on LatchBio Capabilities v1.0
LatchBio Capabilities v1.0 Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  xAI | — | 500K | $2.00 / $6.00 |
Sub-benchmarks
LatchBio SingleCellBench
LatchBio SingleCellBench tests analysis of single-cell RNA sequencing data across problems spanning standard workflows such as labeling cell types, finding differentially expressed genes, and correcting batch effects.
LatchBio SpatialBench Verified
LatchBio SpatialBench Verified tests analysis of spatial transcriptomics data across externally validated problems, requiring the model to answer biological questions about the sample from analysis results.
What is LatchBio Capabilities v1.0?
LatchBio Capabilities v1.0 is a cross-benchmark evaluation of agentic biological data analysis. The overall score is the equally weighted mean of observed scores across 11 capability benchmarks.
LatchBio Capabilities v1.0 is a text benchmark evaluating models on science, agents, and biology tasks. LLM Stats tracks 1 models on this benchmark, scored on a 0–1 scale. The current average is 0.4, with the leader at 0.4.
Compare leaders on the best AI for science, best AI for agents and best AI for biology leaderboards.
Current leaders
Grok 4.7 from xAI currently leads the LatchBio Capabilities v1.0 leaderboard with a score of 0.445 across 1 evaluated AI models.
FAQ
Common questions about the LatchBio Capabilities v1.0 benchmark and leaderboard.