Documentation

Methodology

How this independent index turns a public benchmark table into category-level comparisons.

Scope

BP Eval is an independent, read-only index of publicly released benchmark results. It does not run models or represent model providers, and it is not affiliated with LiveBench.

The displayed snapshot contains the 15 highest overall results calculated from the 2026-06-25 public table.

Source

Raw task scores and category definitions come from the official LiveBench website repository. The source release contains 28 model snapshots across 23 tasks grouped into seven categories.

The source file is frozen by date so readers can reproduce the displayed values even after the main leaderboard changes.

Aggregation

Each category score is the arithmetic mean of valid task values assigned to that category. The overall score is the arithmetic mean of the seven category scores: Reasoning, Coding, Agentic Coding, Mathematics, Data Analysis, Language, and Instruction Following.

Displayed values are rounded to one decimal place after aggregation.

Limitations

Benchmarks are snapshots, not universal product rankings. Prompt settings, task selection, provider changes, and evaluation revisions can affect results. Consult the primary source before making consequential decisions.