Claude Fable 5.1 and GPT-6 Astra Tie for Top Score on AI Intelligence Index Spanning 633 Models
Summary
Claude Fable 5.1 and GPT-6 Astra are tied at the top of the Artificial Analysis Intelligence Index v4.3, both scoring 53 out of 633 benchmarked AI models across mathematics, science, coding, and reasoning evaluations.
Key Points
- The Artificial Analysis Intelligence Index v4.3 is a composite benchmark aggregating ten challenging evaluations — including AA-Briefcase, Terminal-Bench v4.0, SciCode, and Humanity's Last Exam — to measure AI capabilities across mathematics, science, coding, and reasoning.
- Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) leads the leaderboard with a top score of 53, tied with Claude Fable 5.1 (Xhigh Effort) and GPT-6 Astra (max), out of 633 models independently benchmarked by Artificial Analysis.
- The index is calculated as a weighted average across four equal 25% categories — agents, coding, general capability, and scientific reasoning — providing a single score for tracking progress toward artificial general intelligence.