ClaimSpy Pilot - Card - Biomedicine: leaderboard
Table 16; 20-claim pilot, 10 per dataset, one run per backbone/condition; ClaimSpy multi-agent scaffold with fixed Claude search/coding agents; agreement with expert gold verdict sign; ambiguity and small sample retained; abstention is not capability score. Metric: Sign accuracy (0–1). Higher is better. Source: https://arxiv.org/html/2610.20457v1
Metric: Sign accuracy (0–1). Source: arxiv.org. Saturation forecast: Estimated already saturated. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 | 1 | #78 |
| 2 | Gemini 3.1 Pro (Preview) | 0.9 | #56 |
| 3 | GPT-6 Sol | 0.7 | #14 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=claimspy-pilot-card-biomedicine · How It Works · Data refreshed daily, snapshot 2026-10-16.