AIEvals

Benchmarks

Protocols (troubleshooting)

Detecting and fixing problems in molecular-biology laboratory protocols under a publisher-defined troubleshooting evaluation.

Life sciencesReported by AnthropicVendor-reported onlyReported by Anthropic

How it is run

Section 8.13.6 generally averages five attempts per problem at max effort with Haiku biology safeguards disabled. Gemini 3.8 Flash was not run on this variant.

What it cannot tell you

Troubleshooting and protocol understanding use different questions; these results reflect underlying capability rather than deployed safeguard behavior.

Why there is no independent table

No independent suite in this dataset runs Protocols (troubleshooting). The numbers below are the ones model publishers report about their own models, which is a different kind of evidence: each publisher chooses its own harness and effort level, so a row is readable on its own and not against the other rows.

Read this with

Other versions of the same evaluation. Versions are not comparable: the task set changes between them.

  • Protocols (understanding V2)Same family. Answering practical questions about applying or adapting real laboratory protocols in Benchling’s Understanding V2 task set.
  • SpatialBench VerifiedSame category. Analyzing spatial transcriptomics and chromatin-accessibility data in challenging real-world bioinformatics tasks from LatchBio.
  • SingleCellBenchSame category. Analyzing single-cell RNA sequencing data in real-world bioinformatics workflows developed by LatchBio.
  • Morphology-to-molecule matchingSame category. Matching four sets of multi-channel liver-cell images to their shuffled molecule-dose perturbations in Axiom Bio’s assay.
  • Medicinal chemistry (ADME)Same category. Selecting compounds with the highest or lowest measured absorption, distribution, metabolism or excretion properties.
  • Protein design (sequence generation)Same category. Generating novel protein sequences that satisfy a variety of design constraints in a protein-design evaluation.

As reported by each publisher

Kept separate per publisher, because the settings are not shared.

Anthropic

Claude Haiku 5.5: system card capability evaluations · 7 October 2026

RankModelScore
2Claude Haiku 5.558.0%
1Claude Sonnet 5.567.3%
3Claude Sonnet 549.9%

Ranks compare reported scores in the same published row; ties share a rank.

Protocols (troubleshooting). §8.13.6: finding and fixing protocol issues; Gemini 3.8 Flash was not evaluated. Haiku biology safeguards off.

Section 8, pages 111–139 of the Haiku 5.5 system card, read 8 October 2026. Values come from exact prose, tables and labelled figures. Unless specified, Haiku uses adaptive thinking at max effort and five trials with evaluation-specific context up to 1M. Each row retains its subset, metric, effort and source notes; no score is assigned to an unspecified SWE-Bench Pro version. Terminal runs use safeguards without fallback and no internet egress. ProgramBench uses filtered tasks and hidden-test pass rate without a time limit. OSWorld partial and strict results use the official 82-task offline subset. CAD uses 0–1 voxel IoU. Healthcare raw and length-adjusted scores stay separate. Life-science results disable Haiku biology safeguards. Independently run figures quoted by Anthropic remain publisher reports here. Missing comparison values are not inferred from rounded charts.

www.anthropic.com/claude-haiku-5-5-system-card

Sources

Every page used for this benchmark, read on 17 October 2026.