Ask HN: Is anyone giving out tokens for benchmarking LLMs? 3 points by emosenkis 1mo ago ↗ HN I'm thinking of benchmarking different models performance playing Nethack and learning the game under different constraints.
[–] codersfocus 1mo ago ↗ LMarena, now https://arena.ai. Not sure if they have API access to automate it though.
1 comment
[ 2.1 ms ] story [ 10.4 ms ] thread