AA GDP.pdf - Insurance - Criterion Pass Rate: leaderboard
Metric: Criterion Pass Rate (%). Source: artificialanalysis.ai. 166 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.8 Flash (High) | 88.05 |
| 2 | Gemini 3.8 Flash (Medium) | 86.19 |
| 3 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | 84.93 |
| 4 | Gemini 3.7 Flash (High) | 84.13 |
| 5 | Muse Spark 1.3 (Max) | 84.06 |
| 6 | Kimi K3 (Max) | 83.63 |
| 7 | Muse Spark 1.3 (xHigh) | 82.56 |
| 8 | Muse Spark 1.2 (xHigh) | 80.48 |
| 9 | GPT-6 (xHigh) | 79.9 |
| 10 | Qwen 3.8 Max (0902) | 79.64 |
| 11 | Gemini 3.8 Flash (Low) | 79.34 |
| 12 | Gemini 3.5 Flash (High) | 78.92 |
| 13 | GPT-6 (Low) | 78.79 |
| 14 | Gemini 3.6 Flash (High) | 78.67 |
| 15 | GPT-6 (High) | 78.48 |
Interactive version: theaggregate.ai/benchmark?slug=aa-gdp-pdf-insurance-criterion-pass-rate · How It Works · Data refreshed daily, snapshot 2026-09-19.