LLM Evaluation & Leaderboards
News on LLM evaluation and benchmarks, covering new tests, methodology changes, leaderboard results, and whether findings can be reproduced.
Explore how researchers and engineering teams test language models before and after deployment. Coverage looks at benchmark design, meaningful comparisons, leaderboard changes, and which results teams can reproduce.
Latest coverage
Articles
NewsMETR says AI models outscored recruited specialists on three benchmark tasks
NewsArtificial Analysis scores Inkling 2 Mini at 20 on its Intelligence Index
NewsOpenAI introduces MedChemBench to test AI on medicinal chemistry
NewsArtificial Analysis puts Gemini 4 Neon one point above Carbon at lower standard-price cost
NewsArtificial Analysis tightens endpoint test as 24 of 103 trail references
NewsArtificial Analysis and Google DeepMind launch benchmark for visual knowledge work
NewsSnowflake makes AI function evaluation and optimization generally available
NewsMLCommons adds agentic and recommendation tests to MLPerf Training v6.1
NewsOpenAI says coding agents finish 46% of two-to-four-hour research tasks unaided
NewsVals finds prompt framing shifts AI targeting in simulations
NewsPerplexity releases BrowseSafe++ benchmark for browser-agent prompt injection
NewsCWE-bench v2 opens 100 public security-repair tasks
Videos
1:02:51Tech TalksOperationalizing LLMs: From Prototype to Production
Yogiraj Awati·Sep 17, 2026
48:04Tech TalksBuilding Trustworthy Financial AI: Governance, Bias, and Mechanistic Insights
Fabrizio Dimino·Sep 17, 2026
4:40AI Demo Jam: Future AGI
Dmytro Spodarets·Apr 15, 2025
1:13:21Evaluating LLM Models for Production Systems: Methods and Practices
Dmytro Spodarets·Feb 28, 2024
1:01:39GPT on a Leash: Evaluating LLM-based Apps & Mitigating Their Risks
Dmytro Spodarets·Dec 15, 2023
42:58Large Language Model Evaluations - What and Why
Dmytro Spodarets·Jul 24, 2023