Show HN: OmnisBench, a re-gradable, open LLM routing benchmark on fresh tasks (github.com) 1 points by fortitudedev 1mo ago ↗ HN
[–] quietraster 1mo ago ↗ fresh tasks plus regrading could make routing benchmarks much harder to game. how often will the task set rotate? [–] [dead] fortitudedev 1mo ago ↗ [flagged]
3 comments
[ 8.9 ms ] story [ 38.9 ms ] thread