Life Insurance Gap and Overlap Benchmark: leaderboard

Gap and overlap analysis of policy documents (2026): the model reads simplified life insurance contracts and labels each scenario and contract pair as covered, denied or not applicable, against outcomes fixed by an ontology and executable queries. Accuracy in percent; higher is better.

Metric: Accuracy (%) of three-way outcome labels (covered, denied, not applicable) over 580 scenario-contract pairs (58 scenarios by 10 life-insurance contracts), against ontology-derived ground truth; text-only, contract text and structured instructions given through each model's public web interface; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 3 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Claude Sonnet 4.687.76#173
2Gap-Overlap ChatGPT-5.3 (checkpoint unspecified)72.93
3Gap-Overlap Gemini-3 (checkpoint unspecified)65.17

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=life-insurance-gap-and-overlap-benchmark · How It Works · Data refreshed daily, snapshot 2026-11-21.