# GDP.pdf w/ Python (Gemini judge) leaderboard

Multimodal & Grounded 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/multimodal-grounded-gdp-pdf-python-gemini-judge

GDP.pdf task-macro rubric pass rate with Python, Gemini judge. Every model the catalog carries a published GDP.pdf w/ Python (Gemini judge) value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Multimodal & Grounded |
| Measure | Mean rubric pass rate |
| Tasks | Professional document prompts with Python |
| Difficulty | Tool-assisted document reasoning |
| Published by | [GDP.pdf](https://surgehq.ai/blog/gdp-pdf-can-100b-ai-models-master-the-documents-that-run-the-world) |

Professional document understanding where the model receives each original PDF in a sandbox with an IPython tool.

## GDP.pdf w/ Python (Gemini judge) ranking

1 model with a published GDP.pdf w/ Python (Gemini judge) 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 | Mean rubric pass rate | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Kimi K3.1 Pro](https://modelscale.dev/models/kimi-3-1-pro) | Moonshot AI | 85.7 | 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.
