LLM Stats (GDPval-AA): leaderboard
GDP validation benchmark testing economic data retrieval and reasoning, measuring accuracy on GDP-related factual questions.
Metric: ELO. Source: llm-stats.com. Saturation forecast: Around December 2027. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5.1 | 1853 | #9 |
| 2 | GLM-5.3 Flash | 1773 | #65 |
| 3 | GLM-5.3 | 1769 | #39 |
| 4 | Muse Spark 1.3 | 1754 | #24 |
| 5 | Grok 4.6 | 1753 | #26 |
| 6 | Hy4 preview | 1678 | #38 |
| 7 | Gemini 3.8 Flash | 1545 | #21 |
| 8 | Gemini 3.7 Flash | 1525 | #23 |
| 9 | Muse Spark Open | 1401 | #54 |
| 10 | Inkling Small | 1269 | #138 |
| 11 | Inkling | 1238 | #126 |
| 12 | Nemotron 3.5 Super VL (BF16) | 1211 | #165 |
| 13 | Ling-3.0-flash | 1107 | #206 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-gdpval-aa · How It Works · Data refreshed daily, snapshot 2026-10-20.