Today for AI
HOT RADAR
llmHEAT 38.3°

AI CURATED HOT STORY · 10/28/2026

Artificial Analysis Launches v5 Intelligence Index with Anti-Contamination Focus

2 reports archived2 independent sourcesupdated 10/28/2026, 10:11:22
Synthesis & Latest Updates
2 Sources Cross-Validated

Artificial Analysis has released the major upgrade to its Intelligence Index, version 5, fundamentally shifting 60% of evaluation weight to private test sets or datasets with withheld answers. This strategic move aims to mitigate data contamination risks, ensuring scores reflect genuine generalization capabilities on unseen data rather than memorized benchmarks.

Technically, v5 introduces two new benchmarks: Cognition’s FrontierCode 2.0 for real-world code merging tasks and Terminal-Bench-Science for scientific agent tasks. Concurrently, the launch of Progress Index v1 provides a single continuous scale to track long-term model capability evolution, addressing the limitations of static snapshots in capturing dynamic trends.

This update significantly impacts the AI ecosystem by offering developers and enterprises a more credible selection tool. By prioritizing anti-contamination measures and practical application scenarios, the v5 Index establishes a rigorous methodological foundation for objectively measuring sustained progress in AI capabilities.

LATEST/Artificial Analysis officially launched the v5 Intelligence Index, emphasizing anti-contamination via private data, adding code and science benchmarks, and introducing Progress Index v1 for long-term capability tracking.

Hourly heat curve

2 fully observed hours
Fewer than 3 fully observed hours; trend not plotted yet.

Coverage timeline

Total 2 reports · Latest first
  1. Artificial Analysis (@ArtificialAnlys)T1·78 pts

    Artificial Analysis Launches Intelligence Index v5 with Private Benchmarks

    • 60% of Intelligence Index v5 is based on private test sets or held-out answers, significantly reducing data contamination risks
    • Two key benchmarks added: FrontierCode 2.0 (code merge standard) and Terminal-Bench-Science (research tasks)
    • Progress Index v1 launched simultaneously, offering a single continuous scale to track long-term model capability evolution
  2. Artificial AnalysisT1·78 pts

    Artificial Analysis Launches Intelligence Index v5 with Private Datasets and New Code Benchmarks

    • 60% of v5 evaluations are based on private test sets or held-out answers, significantly reducing data contamination risks
    • Two new benchmarks introduced: FrontierCode 2.0 (real-world coding) and Terminal-Bench-Science (agentic scientific tasks)
    • Launch of Progress Index v1 provides a single continuous scale to track long-term model capability evolution