rewirebio.iobenchmarks
Source

How good is AI at molecular biology? (Benchling announcement)

Blog post dated 30 October 2026, as served on 2026-11-06 · Project source

Original source

What this source contributed

Records in this release that cite this source. A record can cite several sources.

Claims

Statements this source supports, each with where in the source it was checked.

  • BenchBench-Cloning: announcement characterisation: Announcement characterisation The Benchling announcement says Kimi K3's 8.8% highlights the gap between frontier and open-weight models at this task (Benchling announcement, paragraph beginning 'GPT-6 Astra led with a score of 30.6%')

Models, benchmarks and other records

Benchmarks (1)

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

27 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance
Artifact SHA-256
eb67d3c73b14e40232bb5ea7633c64572c893c60b4f22a225320dcbac20354bf
Source metadata
How good is AI at molecular biology? (Benchling announcement)

Original source ↗

No field-specific location recorded

Version: Blog post dated 30 October 2026, as served on 2026-11-06
Retrieved: 2026-11-06T11:51:23Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.artifact_sha256

Source artifact SHA-256: eb67d3c73b14e40232bb5ea7633c64572c893c60b4f22a225320dcbac20354bf

Hash scope: Hash scope not separately documented; inspect source record

Evidence concerns
1 values
  • applies to
    • benchbench-cloning-20261106-claim-announcement-open-weight-gap
    artifact sha256
    eb67d3c73b14e40232bb5ea7633c64572c893c60b4f22a225320dcbac20354bf
    message
    The post says Kimi K3's 8.8% highlights "the gap between frontier and open-weight models at this task". The preprint's own Table 2 puts Gemini 3.8 Flash, a hosted frontier model, at 8.6%, below Kimi K3. The characterisation is not supported by the paper's ranking, so claims resting on the post's framing are withheld from comparison.
    review date
    2026-11-06
    source id
    benchbench-cloning-20261106-source-benchling-announcement
    source locator
    Benchling announcement, paragraph beginning 'GPT-6 Astra led with a score of 30.6%'
Source metadata
How good is AI at molecular biology? (Benchling announcement)

Original source ↗

No field-specific location recorded

Version: Blog post dated 30 October 2026, as served on 2026-11-06
Retrieved: 2026-11-06T11:51:23Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.evidence_concerns

Source artifact SHA-256: eb67d3c73b14e40232bb5ea7633c64572c893c60b4f22a225320dcbac20354bf

Hash scope: Hash scope not separately documented; inspect source record

Limitations
3 values
  • Mutable company web page; the hash describes one retrieval.
  • Announcement, not a primary record of the evaluation: it prints no denominators, confidence intervals or per-task results.
  • The post gives no link to the benchmark repository.
Source metadata
How good is AI at molecular biology? (Benchling announcement)

Original source ↗

No field-specific location recorded

Version: Blog post dated 30 October 2026, as served on 2026-11-06
Retrieved: 2026-11-06T11:51:23Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.limitations

Source artifact SHA-256: eb67d3c73b14e40232bb5ea7633c64572c893c60b4f22a225320dcbac20354bf

Hash scope: Hash scope not separately documented; inspect source record

Media type
text/html
Source metadata
How good is AI at molecular biology? (Benchling announcement)

Original source ↗

No field-specific location recorded

Version: Blog post dated 30 October 2026, as served on 2026-11-06
Retrieved: 2026-11-06T11:51:23Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.media_type

Source artifact SHA-256: eb67d3c73b14e40232bb5ea7633c64572c893c60b4f22a225320dcbac20354bf

Hash scope: Hash scope not separately documented; inspect source record

Missing metadata: licence: note
Benchling web page, all rights reserved; hashed, not stored.
Source metadata
How good is AI at molecular biology? (Benchling announcement)

Original source ↗

No field-specific location recorded

Version: Blog post dated 30 October 2026, as served on 2026-11-06
Retrieved: 2026-11-06T11:51:23Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.missing_metadata.licence.note

Source artifact SHA-256: eb67d3c73b14e40232bb5ea7633c64572c893c60b4f22a225320dcbac20354bf

Hash scope: Hash scope not separately documented; inspect source record

Missing metadata: licence: reason
unreported
Source metadata
How good is AI at molecular biology? (Benchling announcement)

Original source ↗

No field-specific location recorded

Version: Blog post dated 30 October 2026, as served on 2026-11-06
Retrieved: 2026-11-06T11:51:23Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.missing_metadata.licence.reason

Source artifact SHA-256: eb67d3c73b14e40232bb5ea7633c64572c893c60b4f22a225320dcbac20354bf

Hash scope: Hash scope not separately documented; inspect source record

Publication status
official_project_source
Source metadata
How good is AI at molecular biology? (Benchling announcement)

Original source ↗

No field-specific location recorded

Version: Blog post dated 30 October 2026, as served on 2026-11-06
Retrieved: 2026-11-06T11:51:23Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.publication_status

Source artifact SHA-256: eb67d3c73b14e40232bb5ea7633c64572c893c60b4f22a225320dcbac20354bf

Hash scope: Hash scope not separately documented; inspect source record

Retrieved at
2026-11-06T11:51:23Z
Source metadata
How good is AI at molecular biology? (Benchling announcement)

Original source ↗

No field-specific location recorded

Version: Blog post dated 30 October 2026, as served on 2026-11-06
Retrieved: 2026-11-06T11:51:23Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.retrieved_at

Source artifact SHA-256: eb67d3c73b14e40232bb5ea7633c64572c893c60b4f22a225320dcbac20354bf

Hash scope: Hash scope not separately documented; inspect source record

Review: artifact sha256
eb67d3c73b14e40232bb5ea7633c64572c893c60b4f22a225320dcbac20354bf
Source metadata
How good is AI at molecular biology? (Benchling announcement)

Original source ↗

No field-specific location recorded

Version: Blog post dated 30 October 2026, as served on 2026-11-06
Retrieved: 2026-11-06T11:51:23Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.review.artifact_sha256

Source artifact SHA-256: eb67d3c73b14e40232bb5ea7633c64572c893c60b4f22a225320dcbac20354bf

Hash scope: Hash scope not separately documented; inspect source record

Review: date
2026-11-06
Source metadata
How good is AI at molecular biology? (Benchling announcement)

Original source ↗

No field-specific location recorded

Version: Blog post dated 30 October 2026, as served on 2026-11-06
Retrieved: 2026-11-06T11:51:23Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.review.date

Source artifact SHA-256: eb67d3c73b14e40232bb5ea7633c64572c893c60b4f22a225320dcbac20354bf

Hash scope: Hash scope not separately documented; inspect source record

How to read the evidence

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: source checked

Benchling's announcement of the BenchBench-Cloning release, which gives the headline aggregate scores and situates the benchmark in the wider BenchBench suite.

1 source record and release history

Read original source

Download this release (gzip)
Technical metadata and extraction receipts

Stable ID: benchbench-cloning-20261106-source-benchling-announcement

areas
dna-genomes
contexts
research
artifact sha256
eb67d3c73b14e40232bb5ea7633c64572c893c60b4f22a225320dcbac20354bf
evidence concerns
applies to: benchbench-cloning-20261106-claim-announcement-open-weight-gap; artifact sha256: eb67d3c73b14e40232bb5ea7633c64572c893c60b4f22a225320dcbac20354bf; message: The post says Kimi K3's 8.8% highlights "the gap between frontier and open-weight models at this task". The preprint's own Table 2 puts Gemini 3.8 Flash, a hosted frontier model, at 8.6%, below Kimi K3. The characterisation is not supported by the paper's ranking, so claims resting on the post's framing are withheld from comparison.; review date: 2026-11-06; source id: benchbench-cloning-20261106-source-benchling-announcement; source locator: Benchling announcement, paragraph beginning 'GPT-6 Astra led with a score of 30.6%'
limitations
Mutable company web page; the hash describes one retrieval.; Announcement, not a primary record of the evaluation: it prints no denominators, confidence intervals or per-task results.; The post gives no link to the benchmark repository.
media type
text/html
missing metadata
licence: note: Benchling web page, all rights reserved; hashed, not stored.; reason: unreported
publication status
official_project_source
retrieved at
2026-11-06T11:51:23Z
review
artifact sha256: eb67d3c73b14e40232bb5ea7633c64572c893c60b4f22a225320dcbac20354bf; date: 2026-11-06; method: source-hash-verification; automated-source-review; note: Fetched on 2026-11-06 and hashed. Its 30.6%, 22.2%, 20.5%, 8.8%, 72% and 27% figures were checked against Tables 2 and G1 of the preprint and agree; its open-weight framing does not, and is recorded as an evidence concern.; retrieval url: https://www.benchling.com/blog/how-good-is-ai-at-molecular-biology; reviewer: claude; reviewer note: Claude (Opus 5) extraction agent. Extraction only: no independent review is claimed, and a different agent reviews this batch.
source locator
Whole post, by Ashu Singhal, posted 30 October 2026
url
https://www.benchling.com/blog/how-good-is-ai-at-molecular-biology
version
Blog post dated 30 October 2026, as served on 2026-11-06
Related records

Suggest a correction