SShogo Bench

GDPval

Deliverables from 44 occupations judged blind against expert human work. Score is win rate.

Agent Index weight
7%
in the Knowledge-work agents pillar
Models tested
11
from the benchmark’s leaderboard and reports
Normalised for the index
0 → 0, 1 → 100
Official site

Results

#ModelScoreNormalisedHarnessCost/taskDate
1GPT-5.2 Supported
OpenAI
49.7%source——
2Claude Opus 4.5 (latest) Supported
Anthropic
45.5%source——
3Claude Opus 4.1 (latest) Supported
Anthropic
43.6%source——
4Claude Sonnet 4.5 (latest) Supported
Anthropic
42.5%source——
5Gemini 3 Pro Preview Supported
Google
40.3%source——
6GPT-5 Supported
OpenAI
34.8%source——
7o3 Supported
OpenAI
30.8%source——
8o4-mini Estimated
OpenAI
25.3%source——
9Gemini 2.5 Pro Supported
Google
23.3%source——
10Grok 4 Supported
xAI
21.1%source——
11GPT-4o (2024-08-06) Supported
OpenAI
9.9%source——

For models without a GDPval result, the index estimates one from Epoch’s Capabilities Index using a logistic fit on 11 models (residual SD 0.34 on the logit scale). Estimates are labelled and widen the model’s range.