BlogLLM Benchmark Scores as Published, Side by Side
Morphology-to-molecule matching (Axiom Bio): Results as Published
Every result the catalog holds for Morphology-to-molecule matching (Axiom Bio): 7 models from 2 developers, read from 2 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Science and MathMaintainer Axiom BioIntroduced 2026Data version 2026103001, as of 2026-10-30
Matches four sets of multi-channel cell images from a human liver in-vitro assay to the four shuffled molecule-dose perturbations that treated the wells.
Not checked against a maintainer's page.
Morphology-to-molecule matching
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6 AstraOpenAI, released 2026-09-03 | 22.8% | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25 | - |
| Claude Sonnet 5.5Anthropic, released 2026-09-28 | 25% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | Effort: max |
| Claude Opus 5.5Anthropic, released 2026-09-22 | 34% | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25 | - |
| Claude Fable 5.1Anthropic, released 2026-09-01 | 25.8% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | Effort: max |
| Claude Mythos 5.1Anthropic, released 2026-09-01 | 25.8% | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25 | - |
| Claude Opus 5Anthropic, released 2026-07-24 | 25% | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25 | - |
| Claude Sonnet 5Anthropic, released 2026-06-30 | 6.8% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19; printed on 1 more page | Effort: max |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.