# ProgramBench (binary) leaderboard

Coding benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/coding-program-bench-binary

ProgramBench binary score (task counts only at 95% or higher). Every model the catalog carries a published ProgramBench (binary) value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Coding |
| Measure | Share of tasks at 95% or higher |
| Tasks | Cleanroom executable reimplementation |
| Difficulty | Whole-program reconstruction |
| Published by | [ProgramBench](https://www.vals.ai/benchmarks/programbench) |

ProgramBench cleanroom reimplementation tasks scored as pass/fail: a task counts only when its ProgramBench score is at least 95%.

## ProgramBench (binary) ranking

1 model with a published ProgramBench (binary) value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Share of tasks at 95% or higher | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Kimi K3.1 Pro](https://modelscale.dev/models/kimi-3-1-pro) | Moonshot AI | 31.5 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
