add reproducible cross-model benchmark matrix (#107)
This commit is contained in:
1 parent
58193d688d
commit
937c6e9837
10 files changed
+842
-4
No files matched your search
+4
-1
@@ -13,6 +13,9 @@
|
||||
"setup:api": "bash scripts/setup-api.sh",
|
||||
"doctor": "node scripts/doctor.mjs",
|
||||
"verify-claims": "node scripts/verify-claims.mjs",
|
||||
"bench:model-matrix": "node scripts/model-matrix.mjs",
|
||||
"verify:model-matrix": "node scripts/model-matrix.mjs --verify",
|
||||
"test:model-matrix": "node scripts/model-matrix.mjs --self-test && node scripts/test-model-matrix.mjs",
|
||||
"disclose": "node scripts/disclosure-gen.mjs",
|
||||
"test:disclose": "node scripts/test-disclosure-gen.mjs",
|
||||
"verify-finding": "node scripts/verify-finding.mjs",
|
||||
@@ -59,7 +62,7 @@
|
||||
"docs:check": "npm run docs:build && node scripts/check-pagenary-docsite.mjs",
|
||||
"mcp": "tsx src/mcp-server.ts",
|
||||
"mcp:prod": "node dist/mcp-server.js",
|
||||
"test": "vitest run src && node scripts/test-ops-preflight.mjs",
|
||||
"test": "vitest run src && node scripts/test-ops-preflight.mjs && node scripts/test-model-matrix.mjs && node scripts/refusal-frontier.mjs --self-test",
|
||||
"test:coverage": "vitest run --coverage",
|
||||
"test:watch": "vitest src",
|
||||
"lint": "eslint src/**/*.ts",
|
||||
|
||||
Reference in new issue
Block a user