BLOG

Insights, updates, and deep dives into LLM benchmarking, AI evaluation, and the latest trends in artificial intelligence.

Introducing AutoBench 2.0: Our New Benchmarking Platform is Out Just in Time to Evaluate GPT 5.2.

We are also announcing our latest benchmark (Run 5) made possible by new platform features for more powerful and efficient benchmarking: Random Score Pooling, Nonlinear Weighting, Parallel Iteration.

LeaderboardLLMBenchmarking

AutoBench Team•December 17, 2025•5 min read

AutoBench Goes to the Farm with Evja: The First Ever Agronomy Benchmark. The Best Farmer LLM? OpenAI, but Mistral...

We teamed up with leading agritech company EVJA to drop the first-ever LLM benchmark dedicated to the agricultural sector. 40 models, 4 professional personas, and one major open-source surprise.

LeaderboardLLMBenchmarking

AutoBench Team•December 10, 2025•5 min read

AutoBench Run 4 is out with Gemini 3 Pro, Gpt 5.1, Grok 4.1 etc. And the winner is not who you expect

This run evaluated 33 models across over 300 iterations (generated questions) using 21 ranking models and generating over 220,000 individual rankings.

LeaderboardValidationLLM

AutoBench Team•November 28, 2025•5 min read

AutoBench Goes Scientific: Rigorous Validation for a Dynamic, Open-Source LLM Benchmark

We're thrilled to announce that AutoBench has moved from a promising open-source project to a scientifically validated framework, with our first paper published in collaboration with Sapienza University of Rome.

ResearchValidationLLM

AutoBench Team•October 29, 2025•5 min read