VulcanBench
@VulcanBench
Benchmarking models across effort levels and harnesses on eval suites with real coding tasks. Because you don't need High or Max effort as much as you think.
参加 March 2020
73 フォロー中 2.8K ファン
🖖 VulcanBench v0.10.0 is out
Here's what's new:
• Every run now logs its tool calls, one schema across 11 harnesses
• vulcanbench tool-calls backfills older runs
• New Mirror harness for Reflection Beam, with full traces
Now live on Github:
もっと見る
