Safety-gated capabilities matrix
Editorial encoding of published model-safety policies (allowed / gated / blocked).
About this data
An editorial encoding of each model’s published safety policy across sensitive domains (cyber, bio, chem and others), scored allowed / gated / blocked. It reflects each lab’s stated policy, not measured model behavior, and is meant for comparison rather than as a benchmark.
For each model × domain: allowed (green) / safety-gated (amber) / blocked (red).
View data & sources →Data table
| bio | chem | cyber | legal | model | series | medical | source_ref | value_basis |
|---|---|---|---|---|---|---|---|---|
| 1 | 1 | 1 | 3 | Claude Fable 5 | safety_matrix | 2 | anthropic-news | Topics_Content/07_New_Trending_Topics_2026.md §1.2 — hard limits block high-risk cyber/bio/chem (fallback to Opus 4.8); editorial 1=blocked/2=gated/3=allowed |
| 2 | 2 | 2 | 3 | Claude Opus 4.8 | safety_matrix | 2 | anthropic-news | ASL-3-style gating on CBRN/cyber per model card; editorial encoding |
| 2 | 2 | 2 | 3 | Frontier baseline (typical) | safety_matrix | 2 | stanford-hai-2024 | Typical frontier-lab usage-policy posture; editorial encoding |
Methodology & sources
Last updated: Jul 17, 2026Methodology
Source-backed values are seeded for four of the five charts: the release cadence by lab (2024 → 2026, from each lab’s release notes), the capability-vs-cost scatter (Artificial Analysis Intelligence Index vs output $/M tokens, June 2026 snapshot), training-compute growth by year (Epoch AI, corroborated by Stanford HAI), and a safety-gated capabilities matrix. Every numeric point carries a sources[].ref and a value_basis. Sources are each lab’s own model cards/release notes, Artificial Analysis, Epoch AI, and Stanford HAI — cross-checked against public release timelines. EDITORIAL ENCODING: the safety-gated matrix scores each model × domain as 3 = allowed / 2 = gated / 1 = blocked. This is an interpretation of each model’s published safety policy, not a measured benchmark. PLACEHOLDER: the per-lab benchmark-trajectory chart is left unseeded — a consistent historical per-quarter, per-lab benchmark series was not sourceable without mixing incompatible benchmarks. Re-verified 2026-06-15.
Sources
- Anthropic Model Cards & Release Notes ↗ Publicly available
- Stanford HAI — AI Index Report ↗ CC BY-ND 4.0 — attribution required
Comparisons are informative, not definitive. See each source for definitions and limits.