Domains: BusinessFinanceLegalMedicalHumanities
Skills: Knowledge WorkAgenticTool UseWritingReasoningMultimodal

Four-Factor Integrity Breakdown & Primary-Source Evidence

Privacy

Weight 40%
0/10
Access Model: Public Plaintext
"We base our evaluation on the public gold OpenAI GDPval dataset from https://huggingface.co/datasets/openai/gdpval"

Originality

Weight 25%
10/10
Reuse Profile: All Original (0% reuse)
"GDPval-AA v2.1 is Artificial Analysis' evaluation framework for OpenAI's GDPval dataset. It assesses language models' capabilities on economically valuable tasks, covering 44 occupations across key sectors contributing to GDP in the United States."

Freshness

Weight 20%
1.5/10
Initial Release: 2025-10Latest Refresh: 2025-10Rolling Updates: No
"arXiv:2510.04374 (cs) [Submitted on 5 Oct 2025] Title: GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks"
Primary source (Paper) ↗ Verified 2026-11-17

Grading

Weight 15%
3.3/10
Integrity: Self-Reported / Live NetworkSandbox: live internet
"GDPval-AA v2.1 is Artificial Analysis' evaluation framework for OpenAI's GDPval dataset. It tests AI models on real-world tasks across 44 occupations and 9 major industries. Models are given shell access and web browsing capabilities in an agentic loop via Stirrup to solve tasks, with Elo ratings derived from blind pairwise comparisons."

Frontier Model Standings on GDPval-AA v2.1

Top 15 active models tracked
Rank Model Official Score Percentile
#1Claude Opus 5.5 max Anthropic1866 Elo96.1p
#2Kimi K3.1 Pro max Kimi1861 Elo93.8p
#3Muse Wonder Full max Meta1857 Elo91.4p
#4Claude Sonnet 5.5 max Anthropic1838 Elo89.1p
#5Claude Fable 5.2 max Anthropic1831 Elo86.8p
#6Qwen4 Max xhigh Alibaba1809 Elo84.4p
#7Muse Wonder max Meta1770 Elo82.0p
#8Claude Fable 5.1 max Anthropic1764 Elo79.6p
#9DeepSeek V4.1 Flash 1017 max DeepSeek1746 Elo77.4p
#10Gemini 4 Carbon high Google1733 Elo75.0p
#11Grok 4.7 xhigh SpaceXAI1717 Elo72.6p
#12MiMo-V2.6-Pro default Xiaomi1692 Elo70.3p
#13Muse Spark 1.3 max Meta1681 Elo67.9p
#14Qwen3.8 Max (0902) xhigh Alibaba1674 Elo65.5p
#16Ling 3.1 Flash 1019 default InclusionAI1655 Elo60.9p

Embeddable Audit Badge

View Markdown (.md)

Benchmark maintainers can embed this live SVG badge in GitHub READMEs or documentation:

BenchAudit GDPval-AA v2.1 Tier C 3.3/10
[![BenchAudit Tier C](https://benchaudit.org/badges/gdpval-aa-v2-1.svg)](https://benchaudit.org/benchmarks/gdpval-aa-v2-1/)