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

Artificial Analysis's implementation of Surge AI's GDP.pdf restricted to its Insurance 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
1Gemini 4 Carbon (High)89.13#1 (Gemini 4 Carbon)
2Gemini 4 Argon (High)88.24#9 (Gemini 4 Argon)
3Gemini 3.8 Flash (High)88.05#30 (Gemini 3.8 Flash)
4Gemini 3.8 Flash (Medium)86.19#30 (Gemini 3.8 Flash)
5Claude Opus 5 (Max)84.93#16 (Claude Opus 5)
6Claude Opus 5 (xHigh)84.93#16 (Claude Opus 5)
7Muse Wonder Full (Max)84.25#12 (Muse Wonder Full)
8Gemini 3.7 Flash (High)84.13#24 (Gemini 3.7 Flash)
9Muse Spark 1.3 (Max)84.06#31 (Muse Spark 1.3)
10Kimi K3 (Max)83.63#35 (Kimi K3)
11Claude Opus 5 (Medium)83.32#16 (Claude Opus 5)
12Claude Opus 5 (High)82.94#16 (Claude Opus 5)
13Muse Spark 1.3 (xHigh)82.56#31 (Muse Spark 1.3)
14Muse Spark 1.2 (xHigh)80.48#69 (Muse Spark 1.2)
15Claude Haiku 5.5 (Max)80.17#43 (Claude Haiku 5.5)

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

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