# Artificial Analysis GDP.pdf (GDP.pdf)

> Artificial Analysis' document-output benchmark: professional tasks whose deliverable is a produced PDF, one of the ten components of its Intelligence Index v4.3.

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

- Category: [Agentic](/agentic)
- Last updated: September 27, 2026

## About GDP.pdf

- Year: 2026
- Tasks: Professional document-production tasks
- Format: Task success rate
- Difficulty: Professional knowledge work
- Paper: [GDP.pdf Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/gdp-pdf)

Independently run by Artificial Analysis under its published harness. Display-only; not yet admitted as independent-run evidence.

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

## Leaderboard (14 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [GPT-6 Astra](/models/gpt-6-astra) | OpenAI | 31.0% |
| 2 | [GPT-5.6 Sol](/models/gpt-5-6-sol) | OpenAI | 27.2% |
| 3 | [Muse Spark 1.3](/models/muse-spark-1-3) | Meta | 26.6% |
| 4 | [Claude Opus 5.5](/models/claude-opus-5-5) | Anthropic | 26.2% |
| 5 | [Claude Fable 5.1](/models/claude-fable-5-1) | Anthropic | 26.2% |
| 6 | [GPT-6 Sol](/models/gpt-6-sol) | OpenAI | 24.8% |
| 7 | [GPT-5.6 Luna](/models/gpt-5-6-luna) | OpenAI | 24.0% |
| 8 | [Kimi K3](/models/kimi-k3) | Moonshot AI | 22.0% |
| 9 | [Claude Opus 5](/models/claude-opus-5) | Anthropic | 21.6% |
| 10 | [Gemini 3.8 Flash](/models/gemini-3-8-flash) | Google | 21.0% |
| 11 | [GPT-6 Luna](/models/gpt-6-luna) | OpenAI | 20.4% |
| 12 | [Grok 4.7](/models/grok-4-7) | xAI | 20.0% |
| 13 | [MiMo-V2.6-Pro](/models/mimo-v2-6-pro) | Xiaomi | 19.2% |
| 14 | [Grok 4.6](/models/grok-4-6) | xAI | 17.0% |

## FAQ

### What does GDP.pdf measure?

Artificial Analysis' document-output benchmark: professional tasks whose deliverable is a produced PDF, one of the ten components of its Intelligence Index v4.3.

### Which model scores highest on GDP.pdf?

GPT-6 Astra by OpenAI currently leads with a score of 31.0% on GDP.pdf.

### How many models are evaluated on GDP.pdf?

14 AI models have been evaluated on GDP.pdf on BenchLM.

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

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

## Compare Top Models on GDP.pdf

- [GPT-6 Astra vs GPT-5.6 Sol](/compare/gpt-5-6-sol-vs-gpt-6-astra)
- [GPT-5.6 Sol vs Muse Spark 1.3](/compare/gpt-5-6-sol-vs-muse-spark-1-3)
- [Muse Spark 1.3 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-muse-spark-1-3)
- [Claude Opus 5.5 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-claude-opus-5-5)