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

Meta accused of using unreleased Llama 4 variants to boost AI benchmark rankings, prompting LM Arena policy changes.

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

More recently, Meta fine-tuned a version of one of its newer models, Llama 4 Maverick, to perform well on a particular benchmark, LM Arena. The vanilla version of the model scores significantly ...

More recently, Meta fine-tuned a version of one of its newer models, Llama 4 Maverick, to perform well on a particular benchmark, LM Arena. The vanilla version of the model scores significantly worse ...