GDPval
Win rate against industry professionals on economically valuable tasks (OpenAI).
- Published by
- OpenAIdata via Epoch AI Benchmarking Hub
- Category
- Agents & tools
- Index weight
- 0.5
- Models
- 11
- Data as of
- 9 Sept 2026
CC BY 4.0 — Epoch AI, ‘AI Benchmarking Hub’, epoch.ai/benchmarks. Mirrored boards credit their original publishers.
- 1GPT-5.249.7%
- 2Claude Opus 4.545.5%
- 3Claude Opus 4.143.6%
- 4Claude Sonnet 4.542.5%
- 5Gemini 3 Pro40.3%
- 6GPT-534.8%
- 7o330.8%
- 8o4-mini25.3%
- 9Gemini 2.5 Pro23.3%
- 10Grok 421.1%
- 11GPT-4o9.9%
11 of 11
| # | |||||
|---|---|---|---|---|---|
| 1 |  GPT-5.2OpenAI | 49.7% | – | 50.1 | – |
| 2 |  Claude Opus 4.5Anthropic | 45.5% | Claude Opus 4.5 | 58.0 | – |
| 3 | Claude Opus 4.1Anthropic | 43.6% | Claude Opus 4.1 | 52.6 | – |
| 4 | Claude Sonnet 4.5Anthropic | 42.5% | Claude Sonnet 4.5 | 52.3 | – |
| 5 |  Gemini 3 ProGoogle | 40.3% | – | 61.6 | – |
| 6 | GPT-5OpenAI | 34.8% | – | 58.5 | – |
| 7 | o3OpenAI | 30.8% | – | 53.6 | – |
| 8 | o4-miniOpenAI | 25.3% | – | 48.0 | – |
| 9 | Gemini 2.5 ProGoogle | 23.3% | Gemini 2.5 Pro | 54.1 | – |
| 10 |  Grok 4xAI | 21.1% | – | – | – |
| 11 | GPT-4oOpenAI | 9.9% | – | 42.3 | – |