CiteTrace - Fidelity Failure Rate: leaderboard
Metric: Fidelity failure rate (%; share of evaluable citations whose cited claim is fabricated or misattributed relative to the crawled source, answer-source fidelity 1-2 on a five-level scale; gpt-4o-mini judge; 11,200 Stack Exchange questions). Source: arxiv.org. Saturation forecast: Around March 2028. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Haiku 4.5 | 12.31 |
| 2 | Claude Sonnet 4.6 | 13.07 |
| 3 | Gemini 3 Flash | 29.97 |
| 4 | Gemini 3.1 Pro (Preview) | 33.07 |
| 5 | Sonar | 34.07 |
| 6 | Grok 4.1 Fast (Non-reasoning) | 40.5 |
| 7 | GPT-5 | 42.29 |
| 8 | Grok 4.1 Fast (Reasoning) | 42.64 |
| 9 | GPT-5 Mini | 44.85 |
Interactive version: theaggregate.ai/benchmark?slug=citetrace-fidelity-failure-rate · How It Works · Data refreshed daily, snapshot 2026-09-26.