Back model benchmark with Braintrust, drop in-house scoring (#13)

# Conflicts:
#	bun.lock
#	package.json
This commit is contained in:
Sinabina
2026-07-21 14:45:13 -07:00
21 changed files with 617 additions and 859 deletions
+3 -1
View File
@@ -106,6 +106,8 @@
],
"devDependencies": {
"@anthropic-ai/claude-agent-sdk": "0.3.216",
"@huggingface/transformers": "4.2.0"
"@huggingface/transformers": "4.2.0",
"autoevals": "^0.3.0",
"braintrust": "^3.24.0"
}
}