OpenAI answer share
share of recommendation answers63.9%
Live chart · updates with every published snapshot
Best AI model score on LiveBench
The highest overall score on LiveBench, an objective benchmark with contamination-resistant questions, held by the current leading model configuration.
LiveBench overall score82.4held by GPT 5.6 Sol Max
View chart data
| As of | LiveBench overall score |
|---|---|
| Jun 25, 23:59 UTC | 82.4 |
About this metric
LiveBench is an objective benchmark that scores exact model configurations across seven categories, including reasoning, coding, mathematics, and data analysis. Questions rotate to resist contamination, and grading is automatic rather than judged by other models. This chart tracks the single best overall score on the board, whichever configuration holds it.
The score is the unweighted mean of the seven LiveBench category averages for each official release, republished here per exact configuration rather than per marketing name. A model listed at high effort or maximum thinking budget is scored as that configuration only. The leader shown beside the number is read live from the current snapshot.
The frontier score is the cleanest single number for how capable publicly available models actually are. Vendor announcements lead with selective evaluations; a rotating, objective benchmark does not care about launch narratives. Watching the ceiling move, and who holds it, is the fastest way to track real capability shifts.
Related charts