We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 9f796a8 commit 60f2126Copy full SHA for 60f2126
evals/buffbench/main-single-eval.ts
@@ -7,8 +7,8 @@ async function main() {
7
8
await runBuffBench({
9
evalDataPaths: [path.join(__dirname, 'eval-codebuff.json')],
10
- agents: ['base2'],
11
- taskIds: ['filter-system-history'],
+ agents: ['base2-free-evals'],
+ taskIds: ['server-agent-validation'],
12
saveTraces,
13
})
14
0 commit comments