GDPval-AA
Progress Over Time
Interactive timeline showing model performance evolution on GDPval-AA
GDPval-AA Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | Anthropic | — | 1.0M | $10.00 / $50.00 | ||
| 2 | Zhipu AI | 320B | 1.0M | $0.15 / $0.50 | ||
| 3 | Zhipu AI | 753B | 1.0M | $1.20 / $4.00 | ||
| 4 | Meta | — | 1.0M | $0.10 / $0.20 | ||
| 5 | xAI | — | 500K | $2.00 / $6.00 | ||
| 6 | Tencent | 770B | — | — | ||
| 7 | Thinking Machines Lab | 594B | 256K | $0.30 / $1.00 | ||
| 8 | Google | — | 1.0M | $0.75 / $3.75 | ||
| 9 | Google | — | 1.0M | $0.75 / $3.75 | ||
| 10 | Institute of Foundation Models | 375B | — | — | ||
| 11 | Meta | 816B | 1.0M | $1.25 / $4.25 | ||
| 12 | Thinking Machines Lab | 276B | 524K | $0.30 / $1.20 | ||
| 13 | Thinking Machines Lab | 975B | 524K | $0.95 / $4.05 | ||
| 14 | Inception | — | 1.0M | $0.10 / $0.35 | ||
| 15 | 120B | 262K | $0.20 / $1.00 | |||
| 16 | InclusionAI | 124B | 131K | $0.06 / $0.18 | ||
| 17 | Meta | 30B | 131K | $0.30 / $1.20 | ||
| 18 | 4B | — | — |
Sub-benchmarks
What is GDPval-AA?
GDPval-AA evaluates AI agents on economically valuable professional knowledge-work tasks and reports performance as an Elo score.
GDPval-AA is a text benchmark evaluating models on legal, reasoning, finance, general, and agents tasks. LLM Stats tracks 18 models on this benchmark, scored on a 0–3000 scale. The current average is 1449.1, with the leader at 1853.0.
Compare leaders on the best AI for legal, best AI for reasoning, best AI for finance, best AI for general and best AI for agents leaderboards.
Current leaders
Claude Fable 5.1 from Anthropic currently leads the GDPval-AA leaderboard with a score of 1853.000 across 18 evaluated AI models.
FAQ
Common questions about the GDPval-AA benchmark and leaderboard.