AA GDP.pdf - Engineering - Criterion Pass Rate: leaderboard

Artificial Analysis's implementation of Surge AI's GDP.pdf restricted to its Engineering domain: the mean share of task-specific atomic criteria satisfied on professional tasks over long PDF documents. Reported 0-100 (%); higher is better. A criterion pass rate, not the all-criteria pass rate shown on the AA GDP.pdf board.

Metric: Criterion Pass Rate (%). Source: artificialanalysis.ai. Saturation forecast: Around February 2027. 242 models tracked.

Top models

#ModelScoreOverall rank
1GPT-6.1 Terra (Low)83.87#15 (GPT-6.1 Terra)
2GPT-6 Astra (xHigh)82.86#6 (GPT-6 Astra)
3GPT-6.1 Terra (High)82.81#15 (GPT-6.1 Terra)
4GPT-6 Astra (Max)82.7#6 (GPT-6 Astra)
5GPT-6.1 Terra (Max)82.6#15 (GPT-6.1 Terra)
6GPT-6.1 Terra (Medium)81.85#15 (GPT-6.1 Terra)
7Gemini 4 Argon (High)81.7#9 (Gemini 4 Argon)
8GPT-6.1 Sol (Medium)81.27#7 (GPT-6.1 Sol)
9GPT-6 Astra (High)81.2#6 (GPT-6 Astra)
10GPT-6 Astra (Medium)80.86#6 (GPT-6 Astra)
11GPT-6.1 Sol (High)80.48#7 (GPT-6.1 Sol)
12GPT-6.1 Sol (Low)80.32#7 (GPT-6.1 Sol)
13GPT-6.1 Sol (Max)80.31#7 (GPT-6.1 Sol)
14GPT-6 Astra (Low)80.03#6 (GPT-6 Astra)
15GPT-6 Sol (xHigh)78.85#19 (GPT-6 Sol)

No result here: #3 Claude Opus 5.5, #10 Claude Fable 5.1.

Interactive version: theaggregate.ai/benchmark?slug=aa-gdp-pdf-engineering-criterion-pass-rate · How It Works · Data refreshed daily, snapshot 2026-11-05.