New: GPT-6.2 benchmark report is here.Read the report ↗

Best LLMs on AAV Capsid Packaging Prediction

AAV Capsid Packaging Prediction

Ranks held-out adeno-associated virus variants by packaging efficiency from labeled sequences and ESM embeddings.

Updated: Data as of:
Limited reportingSaturation: not applicable
Official benchmark
AAV Capsid Packaging Prediction results. Each row identifies its benchmark version and evaluation track. Scores from different versions are not directly comparable. Best effort from the latest stored report date per model and version.
Model / creatorVersionReported score
GPT-6.2 AstraOpenAI · ProprietaryGPT-6.2 system card0.593 coefficient
GPT-6.2 SolOpenAI · ProprietaryGPT-6.2 system card0.574 coefficient
View all 2 published reports
GPT-6.2 Astra0.593 coefficient
GPT-6.2 system card

held out sequences: 1100 · labeled sequences: 5000 · tools: CPU container, Python, web search

OpenAI ↗
GPT-6.2 Sol0.574 coefficient
GPT-6.2 system card

held out sequences: 1100 · labeled sequences: 5000 · tools: CPU container, Python, web search

OpenAI ↗