# GDP.pdf mean criteria pass rate with tools (GDP.pdf (tools))

> Professional document understanding with a container, standard libraries, and image cropping.

Canonical page: https://benchlm.ai/benchmarks/gdppdfwithtools

- Category: [Multimodal & Grounded](/multimodal-grounded)
- Last updated: September 27, 2026

## About GDP.pdf (tools)

- Year: 2026
- Tasks: 100 professional document prompts
- Format: Mean criteria pass rate with tools
- Difficulty: Professional document reasoning
- Paper: [GDP.pdf](https://surgehq.ai/blog/gdp-pdf-can-100b-ai-models-master-the-documents-that-run-the-world)

Section 8.12.4 reports a five-run mean criteria pass rate from Anthropic's corrected internal harness with tools, using Opus 4.7 as judge.

GDP.pdf (tools) is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (1 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Claude Opus 5](/models/claude-opus-5) | Anthropic | 85.5% |

## FAQ

### What does GDP.pdf (tools) measure?

Professional document understanding with a container, standard libraries, and image cropping.

### Which model scores highest on GDP.pdf (tools)?

Claude Opus 5 by Anthropic currently leads with a score of 85.5% on GDP.pdf (tools).

### How many models are evaluated on GDP.pdf (tools)?

1 AI models have been evaluated on GDP.pdf (tools) on BenchLM.

### Does GDP.pdf (tools) affect BenchLM's overall score?

Not directly. GDP.pdf (tools) is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.