Tagged: llm-benchmarks

13 articles

Latest

Meta's Muse Spark 1.3 Cuts Tool Calls 20% but Ships Without Its Best Mode

Google's Gemini 3.8 Flash burns more tokens for accuracy — but don't migrate blindly

Anthropic's Fable 5.1 doubles coding scores but the 45% savings claim is already disputed

Why Your Voice AI Feels Slow Even When Your LLM's TTFT Looks Fast

Mixtral 8x7B Beats Llama 2 70B and GPT-3.5 With an Apache 2.0 License

Soofi S: The 30B German moe model that spanks 70B rivals

Arabic AI Benchmarks Fractured—A New Leaderboard Tries to Unite 700+ Models

Cohere's Aya Expanse 8B beats models twice its size by pitting teacher AIs against each other

Hugging Face's Code Agent Tops GAIA Benchmark, Beating GPT-4 Turbo's 7%

380M Arabic speakers get a leaderboard built to catch what English benchmarks miss

Hebrew LLMs finally get a real benchmark — and most models will likely flunk it

New LLM leaderboard ranks 100+ APIs by speed, price, and quality

Vectara open-sources its hallucination leaderboard using Hugging Face's new template