Skip to content

Evidence: AgentGovBench 48/48 on the current library, beside ACP and the agent tools buyers know - #8

Merged
chrisjleal merged 3 commits into
mainfrom
claude/launch-benchmarks-comparisons-jo34y4
Oct 20, 2026
Merged

chrisjleal merged 3 commits into
mainfrom
claude/launch-benchmarks-comparisons-jo34y4

Conversation

@chrisjleal

@chrisjleal chrisjleal commented Oct 20, 2026 •

Copy link
Copy Markdown
Contributor

Requested by chris · project thread

Before: "What it stops" showed 48 of 48 on the April library against 28 and 13, with no outside comparison.

After: the governance chart shows the current library: Proofable 48, the maintainers' gateway (ACP) 46, allow-everything 20, no governance 5. A second chart in the same style puts Proofable beside Claude Code, Codex CLI and Cursor (13 on their own, 37 and 43 with ACP). The AgentGovBench accordion carries both tables, the sources and what separates the approaches; the standards row uses the current numbers.

How: merged with main's new page layout and chart style. Current-library numbers are from today's run against the engine merged in protocol#38; agent-tool rows are the maintainers' results/ files. The "matched by hash to the live service" wording needs protocol#38 deployed before this merges. Copy, route, public-surface, markdown and OpenAPI checks pass.

🤖 Generated with Claude Code

https://claude.ai/code/session_01DKvJGBSkG8UDNyzRVNzdrS

…nd fix the top button.

The top button pointed at a page that does not exist; it now opens the
pilot page. The AgentGovBench section shows the maintainers' published
results for Claude Code, Codex CLI, Cursor, the OpenAI and Anthropic agent
SDKs, CrewAI and LangGraph on the same library, and the result on the
library's October revision.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DKvJGBSkG8UDNyzRVNzdrS
@chrisjleal chrisjleal self-assigned this Oct 20, 2026
…buyers know.

Proofable passes 48 of 48 on the library as revised in October 2026,
beside the maintainers' gateway at 46. A second chart shows the
maintainers' published results for Claude Code, Codex CLI and Cursor on
the earlier library.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DKvJGBSkG8UDNyzRVNzdrS
@chrisjleal chrisjleal changed the title Evidence: AgentGovBench comparison with Claude Code, Codex, Cursor and agent SDKs; fix top button Evidence: AgentGovBench 48/48 beside ACP and the agent tools buyers know; fix top button Oct 20, 2026
@chrisjleal
chrisjleal marked this pull request as ready for review October 20, 2026 07:56
…ew Evidence page.

The governance chart now shows Proofable 48, the maintainers' gateway 46,
allow-everything 20 and no governance 5. A second chart in the same style
puts Proofable beside Claude Code, Codex CLI and Cursor.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DKvJGBSkG8UDNyzRVNzdrS
@chrisjleal chrisjleal changed the title Evidence: AgentGovBench 48/48 beside ACP and the agent tools buyers know; fix top button Evidence: AgentGovBench 48/48 on the current library, beside ACP and the agent tools buyers know Oct 20, 2026
@chrisjleal
chrisjleal merged commit 991462a into main Oct 20, 2026
2 checks passed
@chrisjleal
chrisjleal deleted the claude/launch-benchmarks-comparisons-jo34y4 branch October 20, 2026 22:37
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants