One of Meta's newest AI models, Llama 4 Maverick, ranks below rivals on a popular chat benchmark. Meta didn't originally ...

The founders of the popular generative artificial intelligence benchmarking platform LMArena have said they’re founding an ...

Meta appears to have used an unreleased, custom version of one of its new flagship AI models, Maverick, to boost a benchmark score.

Meta's Maverick AI takes second in LM Arena but raises eyebrows over its "experimental" version, leaving devs in the dark about its real-world performance.

One of the new flagship AI models Meta released on Saturday, Maverick, ranks second on LM Arena, a test that has human raters compare the outputs of models and choose which they prefer.

Earlier this week, Meta landed in hot water for using an experimental, unreleased version of its Llama 4 Maverick model to achieve a high score on a crowdsourced benchmark, LM Arena. The incident ...