Enter opens the highlighted result. Esc closes.

GDPval leaderboard

GPT-5.2 leads
49.7%
models measured
9
lead over #2
+4.2 pts
median
34.8%

Leader on GDPval · read October 21

1 GPT-5.249.7%

On October 21, 2026, 9 of our catalog's models had a GDPval result, and OpenAI GPT-5.2 led with 49.7%, ahead of Anthropic Claude Opus 4.5 at 45.5%.

Work products from 44 occupations, judged against the work of professionals. The number is the share of comparisons the model won or tied.

Role in the index

GDPval is shown as published and does not feed any of our indexes. Read the methodology

9 models with a result

Original board: Epoch AI benchmarking hub
GDPval results for models in the catalog
# Model Result Evidence Coding index Output $/Mtok
1 GPT-5.2OpenAI 49.7% 55.9 $14.00
2 Claude Opus 4.5Anthropic 45.5% 44.0 $25.00
3 Claude Opus 4.1Anthropic 43.6% Not benchmarked $75.00
4 Claude Sonnet 4.5Anthropic 42.5% 39.5 $15.00
5 GPT-5OpenAI 34.8% 38.8 $10.00
6 o3OpenAI 30.8% Not benchmarked $8.00
7 o4 Mini HighOpenAI 25.3% Not benchmarked $4.40
8 Gemini 2.5 ProGoogle 23.3% 19.1 $10.00
9 GPT-4oOpenAI 9.9% Not benchmarked $10.00

Only models in our catalog are listed, and each appears once with its best published run. 215 rows were read from the source on October 21, 2026, and rows that match no catalog model are left out.