legal benchmark
GDPval-AA Leaderboard
GDPval-AA evaluates AI agents on economically valuable professional knowledge-work tasks and reports performance as an Elo score.
Updated Oct 23, 2026
Models17
Model coverage17
MetricScore
EvidenceB
GDPval-AA Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Score1,853.00 points | Percentile100.00% | Participants17 | EvidenceC | Evaluated |
| Rank02 | ModelZA | Score1,773.00 points | Percentile93.75% | Participants17 | EvidenceC | Evaluated |
| Rank03 | ModelZA | Score1,769.00 points | Percentile87.50% | Participants17 | EvidenceC | Evaluated |
| Rank04 | ModelME | Score1,754.00 points | Percentile81.25% | Participants17 | EvidenceC | Evaluated |
| Rank05 | ModelXA | Score1,753.00 points | Percentile75.00% | Participants17 | EvidenceC | Evaluated |
| Rank06 | ModelTE | Score1,678.00 points | Percentile68.75% | Participants17 | EvidenceC | Evaluated |
| Rank07 | ModelSA | Score1,583.00 points | Percentile62.50% | Participants17 | EvidenceC | Evaluated |
| Rank08 | ModelGO | Score1,545.00 points | Percentile56.25% | Participants17 | EvidenceC | Evaluated |
| Rank09 | ModelGO | Score1,525.00 points | Percentile50.00% | Participants17 | EvidenceC | Evaluated |
| Rank10 | ModelME | Score1,401.00 points | Percentile43.75% | Participants17 | EvidenceC | Evaluated |
| Rank11 | ModelTM | Score1,269.00 points | Percentile37.50% | Participants17 | EvidenceC | Evaluated |
| Rank12 | ModelTM | Score1,238.00 points | Percentile31.25% | Participants17 | EvidenceC | Evaluated |
| Rank13 | ModelIN | Score1,237.20 points | Percentile25.00% | Participants17 | EvidenceC | Evaluated |
| Rank14 | ModelNV | Score1,211.00 points | Percentile18.75% | Participants17 | EvidenceC | Evaluated |
| Rank15 | ModelIN | Score1,107.00 points | Percentile12.50% | Participants17 | EvidenceC | Evaluated |
| Rank16 | ModelME | Score953.00 points | Percentile6.25% | Participants17 | EvidenceC | Evaluated |
| Rank17 | ModelNV | Score946.00 points | Percentile0.00% | Participants17 | EvidenceC | Evaluated |
GDPval-AA Highlights
The leading models and scores on this benchmark.
GDPval-AA Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for GDPval-AA
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is GDPval-AA?
What GDPval-AA measures and how its scores work.
GDPval-AA is a benchmark for evaluating AI agents on economically valuable professional knowledge-work tasks.
It measures performance using the Score metric, reported as an Elo score in points.
Scores are shown in points. This benchmark is not independently verified and has an evidence level of B.
- Family
- GDPval-AA
- Modality
- text
- Primary category
- legal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about GDPval-AA.
Which model scores highest on GDPval-AA?
Claude Fable 5.1 is currently ranked first with 1,853.00 points.
What are the top three models on GDPval-AA?
The current leaders are Claude Fable 5.1 (1,853.00 points), GLM-5.3-Flash (1,773.00 points), and GLM-5.3 (1,769.00 points).
Which GDPval-AA model has the lowest official input price?
Mercury 3 has the lowest matched official input price at $0.10 input / $0.35 output per 1M tokens.
Which models are fastest among GDPval-AA results?
The fastest matched records are Mercury 3 (1,068.00 tok/s via Inception), Gemini 3.7 Flash (409.96 tok/s via Google), and Gemini 3.8 Flash (55.66 tok/s via Google).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.