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
LABBench2: An Improved Benchmark for AI Systems Performing Biology Research. Every model the catalog carries a published LABBench2 value for, ranked by that value.
A benchmark of realistic biology-research tasks involving literature, figures, tables, databases, and bioinformatics files. 7 models in the ModelChoice catalog have a published value.
Each point is a model with a published LABBench2 value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
7 models with a published LABBench2 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 | Aggregate accuracy |
|---|---|---|---|
| 1 | 88.8 | ||
| 2 | 86.2 | ||
| 3 | Anthropic | 84.2 |
What the benchmark measures and how its value is published, from the source’s own record.
LABBench2 (LABBench2: An Improved Benchmark for AI Systems Performing Biology Research) is a knowledge benchmark published by LABBench2: An Improved Benchmark for AI Systems Performing Biology Research. A benchmark of realistic biology-research tasks involving literature, figures, tables, databases, and bioinformatics files. Its evaluation set is described by the source as nearly 1,900 biology-research tasks. The source rates its difficulty as real-world biology research.
Each model's result is published by LABBench2: An Improved Benchmark for AI Systems Performing Biology Research as aggregate accuracy. ModelChoice prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 7 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 | 82.1 |
| 4 | OpenAI | 82.1 |
| 6 | OpenAI | 81.2 |
| 7 | Anthropic | 80.1 |
Evidence key: Observed
Rows are ordered by the value LABBench2: An Improved Benchmark for AI Systems Performing Biology Research 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.