Meta got caught gaming AI benchmarks

https://news.ycombinator.com/rss Hits: 6
Summary

Over the weekend, Meta dropped two new Llama 4 models: a smaller model named Scout, and Maverick, a mid-size model that the company claims can beat GPT-4o and Gemini 2.0 Flash “across a broad range of widely reported benchmarks.”Maverick quickly secured the number-two spot on LMArena, the AI benchmark site where humans compare outputs from different systems and vote on the best one. In Meta’s press release, the company highlighted Maverick’s ELO score of 1417, which placed it above OpenAI’s 4o and just under Gemini 2.5 Pro. (A higher ELO score means the model wins more often in the arena when going head-to-head with competitors.)The achievement seemed to position Meta’s open-weight Llama 4 as a serious challenger to the state-of-the-art, closed models from OpenAI, Anthropic, and Google. Then, AI researchers digging through Meta’s documentation discovered something unusual.In fine print, Meta acknowledges that the version of Maverick tested on LMArena isn’t the same as what’s available to the public. According to Meta’s own materials, it deployed an “experimental chat version” of Maverick to LMArena that was specifically “optimized for conversationality,” TechCrunch first reported.“Meta’s interpretation of our policy did not match what we expect from model providers,” LMArena posted on X two days after the model’s release. “Meta should have made it clearer that ‘Llama-4-Maverick-03-26-Experimental’ was a customized model to optimize for human preference. As a result of that, we are updating our leaderboard policies to reinforce our commitment to fair, reproducible evaluations so this confusion doesn’t occur in the future.“A spokesperson for Meta, Ashley Gabriel, said in an emailed statement that “we experiment with all types of custom variants.”“‘Llama-4-Maverick-03-26-Experimental’ is a chat optimized version we experimented with that also performs well on LMArena,” Gabriel said. “We have now released our open source version and will see how developers customize Lla...

First seen: 2025-04-08 16:25

Last seen: 2025-04-08 21:26