GDPval — leaderboard
Real-world, economically valuable knowledge work tasks across 44 occupations and 9 U.S. GDP sectors.
Metric: Wins/Ties vs Human (self-reported). Source: benchmarklist.com. Status: saturated. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 84.9 |
| 2 | GPT-5.4 | 83 |
| 3 | GPT-5.5 Pro | 82.3 |
| 4 | GPT-5.4 Pro (xHigh) | 82 |
| 5 | Claude Opus 4.7 | 80.3 |
| 6 | Gemini 3.1 Pro (Preview) | 67.3 |
| 7 | GLM-5.1 | 54.7 |
| 8 | DeepSeek V4 Pro | 54.6 |
| 9 | DeepSeek V4 Flash | 50.2 |
| 10 | MiniMax-M2.7 | 47.6 |
| 11 | Claude Opus 4.1 | 47.6 |
| 12 | Nemotron 3 Ultra | 46.7 |
| 13 | GPT-5 | 39 |
| 14 | O3 | 35.2 |
| 15 | Qwen 3.5 397B A17B | 34.6 |
Interactive version: theaggregate.ai/benchmark?slug=gdpval · How the rankings work · Data refreshed daily, snapshot 2026-07-22.