Artificial Analysis announced the launch of Intelligence Index v5, adding two new benchmarks (FrontierCode 2.0 and Terminal-Bench-Science) and upgrading three existing benchmarks, with 60% of the index based on private datasets for the first time. It also released Progress Index v1 to track model capability changes over time.
Ai2 released the research report "Old Ideas, Novel Problems" on the reliability of LLMs in evaluating research idea novelty, along with benchmark, data, code, and an automated evaluation pipeline. Results showed that six LLM judges (GPT-5.1, GPT-5.2, GPT-5.4, Claude Sonnet 4.5, Claude Opus 4.5, Claude Opus 4.6) were significantly affected by small changes in evaluation setup when judging the same ideas.
Surge AI has added Mistral AI's Mistral Large 4 to its sudo L7 benchmark leaderboard for staff-level software engineering, where the model scored 13.3%, ahead of Muse Spark 1.3 (12.2%) and Grok 4.7 (10.6%). sudo L7 is designed to test whether coding agents can exercise the judgment of experienced engineers.