← Benchmarks
GDPval-AA
GDPval-AA evaluates AI agents on economically valuable professional knowledge-work tasks and reports performance as an Elo score.
id gdpval-aa · max 3000 · 12 models reported
| # | Model | Score |
|---|---|---|
| 1 | Claude Fable 5.1 Anthropic | 1853.00 |
| 2 | GLM-5.3-Flash Zhipu AI · open | 1773.00 |
| 3 | GLM-5.3 Zhipu AI · open | 1769.00 |
| 4 | Muse Spark 1.3 Meta | 1754.00 |
| 5 | Grok 4.6 xAI | 1753.00 |
| 6 | Hy4 preview Tencent · open | 1678.00 |
| 7 | Atria Dawn Preview Shanghai AI Laboratory · open | 1583.00 |
| 8 | Gemini 3.8 Flash Google | 1545.00 |
| 9 | Gemini 3.7 Flash Google | 1525.00 |
| 10 | Inkling-Small Thinking Machines Lab · open | 1269.00 |
| 11 | Inkling Thinking Machines Lab · open | 1238.00 |
| 12 | Ling 3.0 Flash InclusionAI | 1107.00 |
