There are a lot of LLM benchmarks but few, if any, harness benchmarks. I am thinking this would be a really good community project to build one. End goal: a leaderboard of harness performance (multiple axis) on a set of diverse real world tasks[1], grouped by underlying models and reasoning eff...
Source: [Hacker News](https://news.ycombinator.com/item?id=49181014)