Factuality and Hallucination Detection on LongFact Concepts
99.7Overall ScoreGPT-5.2 High
Evaluation results
| Method | Links | ||
|---|---|---|---|
| GPT-5.2 High2026.06 | 99.7 | — | |
| GPT-5-miniTier=High2026.06 | 99.5 | — | |
| Claude-Opus-4.52026.06 | 98.8 | — | |
| Gemini-3-FlashTier=High2026.06 | 98.6 | — | |
| Claude-Sonnet-4.52026.06 | 98.5 | — | |
| Gemini-3-pro High2026.06 | 98.5 | — | |
| Seed2.0 Pro2026.06 | 92.8 | — | |
| Seed2.0 Lite2026.06 | 92.4 | — | |
| Seed2.0 Mini2026.06 | 91.4 | — |