Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Knowledge benchmark
Anthropic Protein Design evaluation. Every model the catalog carries a published Protein Design value for, ranked by that value.
Generates novel protein sequences under family, topology, globularity, and structural-motif constraints. 4 models in the ModelScale catalog have a published value.
Each point is a model with a published Protein Design value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
4 models with a published Protein Design value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Composite score |
|---|---|---|---|
| 1 | Anthropic | 64.6 | |
| 2 | Anthropic | 60.2 | |
| 3 | Anthropic | 51.0 |
What the benchmark measures and how its value is published, from the source’s own record.
Protein Design (Anthropic Protein Design evaluation) is a knowledge benchmark published by Claude Opus 5 System Card. Generates novel protein sequences under family, topology, globularity, and structural-motif constraints. Its evaluation set is described by the source as constrained protein-sequence design tasks. The source rates its difficulty as computational protein design.
Each model's result is published by Claude Opus 5 System Card as composite score. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 4 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
| 4 | Anthropic | 42.5 |
Evidence key: Observed
Rows are ordered by the value Claude Opus 5 System Card published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.