Factuality and Hallucination Detection on FactScore
96.1FactScoreGPT-5-mini
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GPT-5-miniTier=High2026.06 | 96.1 | — | |
| Gemini-3-pro High2026.06 | 92.6 | — | |
| Gemini-3-FlashTier=High2026.06 | 92 | — | |
| GPT-5.2 High2026.06 | 91.9 | — | |
| Claude-Opus-4.52026.06 | 91.1 | — | |
| Claude-Sonnet-4.52026.06 | 90.6 | — | |
| Seed2.0 Pro2026.06 | 71.2 | — | |
| Seed2.0 Lite2026.06 | 62.4 | — | |
| Seed2.0 Mini2026.06 | 50.4 | — |