Tag: benchmarks

Apple researchers detail MM1, a series of multimodal LLMs with up to 30B parameters they say achieve state-of-the-art performance across multiple AI benchmarks (Michael Nuñez/VentureBeat)

Apple researchers detail MM1, a series of multimodal LLMs with up to 30B parameters they say achieve state-of-the-art performance across multiple AI benchmarks (Michael Nuñez/VentureBeat)

Michael Nuñez / VentureBeat: Apple researchers detail MM1, a series of multimodal LLMs with up…

By Mike Powers March 17, 2024

Here’s why most AI benchmarks tell us so little

Here’s why most AI benchmarks tell us so little

On Tuesday, startup Anthropic released a family of generative AI models that it claims achieve…

By Mike Powers March 7, 2024

Anthropic says its Claude 3 suite outperforms GPT-4 and Gemini Ultra on some benchmarks, and adds multimodal support for photos and more for the first time (Hayden Field/CNBC)

Anthropic says its Claude 3 suite outperforms GPT-4 and Gemini Ultra on some benchmarks, and adds multimodal support for photos and more for the first time (Hayden Field/CNBC)

Hayden Field / CNBC: Anthropic says its Claude 3 suite outperforms GPT-4 and Gemini Ultra…

By Mike Powers March 4, 2024