Benchmark database
Browse models, benchmarks and use cases. Every number links to the paper, table and checkpoint it came from, with its review status.
benchmarks.rewirebio.ioIndependent benchmarks for biological AI
Every published result for DNA, RNA, protein and cell models, linked to the model checkpoint, the dataset, the protocol and the table it came from. Where papers disagree, the graph says so.
Release 2026-11-17-793d9cca4ad1
What is in the graph
Each record is a node and each relationship is an edge: which checkpoint was evaluated, on which dataset subset, under which protocol, with which metric, reported in which table of which paper. You can follow any number back to its source in a few hops.
RDF with OWL 2 RL reasoning and SHACL validation, using DCAT, schema.org, OBI, ECO, SEPIO and the ML Schema vocabularies. 2.44 million asserted facts, 300,000 inferred, and 15,000 derived facts about disagreements.
Why a graph
When two studies rank the same pair of models in opposite orders, or one result sits far from all the others, the graph flags it as a lead. 197 are open in the current release. Each is a question to investigate, not a verdict.
In October 2026 an AlphaGenome developer told us a splicing result in a recent preprint could not be right. We traced the preprint's scripts and found an off-by-one error. Read alone, that comparison would have misled anyone choosing a splicing model. Against the rest of the graph, it stood out.
Read the investigation| Source | Metric | ESM-1b | EVE |
|---|---|---|---|
| Brandes 2023, variants scored by all methods | ROC-AUC | 0.892 | 0.883 |
| Brandes 2023, ClinVar head to head | ROC-AUC | 0.906 | 0.885 |
| ProteinGym clinical benchmark | ranks EVE above ESM-1b | ||
| Livesey and Marsh 2025 | ranks EVE above ESM-1b | ||
The model developers' own paper ranks ESM-1b first in 6 of 6 comparisons. Two independent sources rank it the other way. See the lead
How it fits together
Agents read new papers, preprints and leaderboards every day. Reviewed records become a versioned release of the graph. Coding agents query that graph, fetch the data they need, and run benchmarks themselves.
Receipted results from a run can be submitted back into the evidence store, so the next release of the graph includes them.
What you can use
Browse models, benchmarks and use cases. Every number links to the paper, table and checkpoint it came from, with its review status.
benchmarks.rewirebio.ioConflicts between papers, found by rules over the graph on every release, with the studies on each side.
See the disagreementsThe graph for coding agents. Full-text search, entity lookup, provenance, ready-made disagreement queries, and SPARQL for anything else.
rdf-kg-mcp on GitHubFind and read genomic data from EGA, ENA, ENCODE, GEO, NCBI, ClinVar, gnomAD and your own files, one region at a time. Now with published synthetic-data protocols and GIAB and HPRC truth sets.
genomics-mcp on GitHubRuns benchmark protocols and model adapters with pinned data, splits and environments, and reports what it scored and what it cost. An MCP server and GPU backend are being built.
rewire-benchmarks on GitHubPlain-language write-ups of new models and benchmarks, and of what our reruns and investigations found.
Read the blogFor coding agents
Install the database server and your agent can answer questions like these from the graph, with sources:
Each server runs on your machine. The database server downloads the current public release; your questions and your data stay local.
/plugin marketplace add rewire-bio/rewire-benchmarks /plugin install bio-model-benchmarks@rewire-benchmarks
claude mcp add rewire-benchmark-graph -- uvx --from git+https://github.com/rewire-bio/rdf-kg-mcp@v0.2.0 rdf-kg-mcp serve https://benchmarks.rewirebio.io/agents/kg.tar.gz
docker run --rm -i \ --mount type=bind,source=/path/to/your/data,target=/data,readonly \ --mount type=volume,source=genomics-mcp-work,target=/work \ ghcr.io/rewire-bio/genomics-mcp:0.1.0
Other install routes: genomics-mcp install guide ยท agent guide
Coverage
Full records, use-case rankings, run recipes we execute ourselves, and Rewire's own benchmarks as they are built: variant interpretation, splicing, regulatory variants, pathogen detection.
Full records and published results, with disagreements tracked: variant effect, structure and design.
Single-cell, spatial, chemistry, antibody and design models are listed with their sources and covered on the blog.
For model developers
When we find a disagreement or a problem in a published comparison involving your model, we raise it with you before we publish it.
If a record is wrong, open an issue on rewire-benchmark-data. Corrections are versioned and the previous value stays visible.
Results are tied to the checkpoint that was tested. When a paper does not say which weights it used, the result stays at the model-family level.
Incompatible benchmarks are never averaged into one leaderboard. Rewire does not build or sell biological models.
From the blog