AIEvals

Benchmarks

Medicinal chemistry (ADME)

Selecting compounds with the highest or lowest measured absorption, distribution, metabolism or excretion properties.

Life sciencesReported by AnthropicVendor-reported onlyReported by Anthropic

How it is run

Section 8.13.3 uses 504 questions with real compound structures; scores average five max-effort attempts, with Haiku biology safeguards disabled.

What it cannot tell you

These compound-ranking questions do not measure experimental drug discovery or clinical effectiveness; results concern the underlying model configuration.

Why there is no independent table

No independent suite in this dataset runs Medicinal chemistry (ADME). 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

Benchmarks in the same category, which usually disagree with this one on purpose.

  • 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.
  • Protein design (sequence generation)Same category. Generating novel protein sequences that satisfy a variety of design constraints in a protein-design evaluation.
  • Protein design (library ranking)Same category. Prioritizing candidate protein designs for experimental testing by ranking members of a design library.
  • Biomedical image analysisSame category. Quantitatively analyzing biomedical competition images across CT, MRI, histopathology, ultrasound, microscopy and other modalities.

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
3Claude Haiku 5.558.0%
1Claude Sonnet 5.565.3%
2Claude Opus 5.563.5%
4Claude Sonnet 541.3%

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

Medicinal chemistry (ADME). §8.13.3: 504 questions about measured ADME properties of compound structures. 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.