reasoning benchmark
GDPval
GDPval is an OpenAI benchmark evaluating AI models on economically valuable, real-world knowledge-work tasks spanning many professional occupations and industries.
Updated Aug 7, 2026
Published models3
Registry coverage3
MetricScore
EvidenceB
GDPval leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | BY | 87.9% | 100.0% | 3 | C | |
| 2 | BY | 82.7% | 50.0% | 3 | C | |
| 3 | NV | 46.7% | 0.0% | 3 | C |
Score distribution
Top published rows on the benchmark's original scale.
GDPval highlights
The top published results on this benchmark's own scale.
What is GDPval?
Definition and scoring fields from the benchmark registry.
GDPval is an OpenAI benchmark evaluating AI models on economically valuable, real-world knowledge-work tasks spanning many professional occupations and industries.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- GDPval
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- gdpval|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about GDPval.
Which model scores highest on GDPval?
Seed 2.1 Pro is currently ranked first with 87.9%.
What does GDPval measure?
GDPval is an OpenAI benchmark evaluating AI models on economically valuable, real-world knowledge-work tasks spanning many professional occupations and industries.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.