Factuality and Hallucination Detection on LongFact Objects
99.2Factuality ScoreGPT-5.2 High
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GPT-5.2 High2026.06 | 99.2 | — | |
| Claude-Opus-4.52026.06 | 99 | — | |
| Claude-Sonnet-4.52026.06 | 98.8 | — | |
| Gemini-3-pro High2026.06 | 98.1 | — | |
| Seed2.0 Pro2026.06 | 92.9 | — | |
| GPT-5-miniTier=High2026.06 | 0.992 | — | |
| Gemini-3-FlashTier=High2026.06 | 0.979 | — | |
| Seed2.0 Lite2026.06 | 0.922 | — | |
| Seed2.0 Mini2026.06 | 0.87 | — |