Claim-level rating prediction on FORA
65.4CIG ScoreGemini-2.5-Flash
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Gemini-2.5-FlashContext=No Knowledge2026.04 | 65.4 | 63.2 | 66.1 | 49.2 | 61 | |
| GPT-5-MiniContext=No Knowledge2026.04 | 64.6 | 54.2 | 44.8 | 46.3 | 52.4 | |
| Qwen3-4BContext=Memory2026.04 | 64.3 | 52.3 | 42.5 | 59.9 | 54.7 | |
| GPT-5-MiniContext=Short Prior2026.04 | 62.2 | 53.9 | 46 | 45.5 | 51.9 | |
| Qwen3-4BContext=Full2026.04 | 62.2 | 57.1 | 46.7 | 59.3 | 56.3 | |
| Qwen3-4BContext=No Knowledge2026.04 | 61.9 | 72.3 | 46.9 | 65.5 | 61.7 | |
| GPT-5Context=No Knowledge2026.04 | 59.4 | 70 | 42.2 | 48.8 | 55.1 | |
| GPT-5-MiniContext=Memory2026.04 | 59.1 | 55.7 | 46.7 | 45.3 | 51.7 | |
| Gemini-2.5-FlashContext=Summary2026.04 | 58.9 | 58.5 | 57.9 | 45.2 | 55.1 | |
| Gemini-2.5-FlashContext=Short Prior2026.04 | 58.8 | 57 | 53.3 | 47.1 | 54 | |
| Qwen3-4BContext=Summary2026.04 | 57.9 | 51.9 | 47.2 | 58.8 | 53.9 | |
| GPT-5Context=Short Prior2026.04 | 57.2 | 62 | 41.7 | 49.5 | 52.6 | |
| GPT-5-MiniContext=Summary2026.04 | 56.9 | 61.7 | 47.5 | 47.2 | 53.3 | |
| Gemini-2.5-FlashContext=Full2026.04 | 56.3 | 61.6 | 62.2 | 47.4 | 56.9 | |
| Gemini-2.5-FlashContext=Memory2026.04 | 56 | 54.3 | 57.5 | 47.6 | 53.9 | |
| GPT-5-MiniContext=Full2026.04 | 55.1 | 57.4 | 45.6 | 43.8 | 50.5 | |
| Gemini-2.5-ProContext=No Knowledge2026.04 | 53.5 | 53.1 | 52.6 | 56.8 | 54 | |
| Qwen3-4BContext=Short Prior2026.04 | 53.5 | 52 | 46.2 | 57.5 | 52.3 | |
| GPT-5Context=Memory2026.04 | 53.1 | 57.4 | 41.9 | 49.6 | 50.5 | |
| Gemini-2.5-ProContext=Full2026.04 | 52.7 | 60.9 | 54.9 | 56.6 | 56.3 | |
| GPT-5Context=Summary2026.04 | 52 | 55.6 | 41.4 | 47.9 | 49.2 | |
| Gemini-2.5-ProContext=Memory2026.04 | 52 | 53.1 | 54.7 | 58.1 | 54.5 | |
| Gemini-2.5-ProContext=Short Prior2026.04 | 51.8 | 53.6 | 56.2 | 55.5 | 54.3 | |
| GPT-5Context=Full2026.04 | 51.2 | 55.6 | 42.9 | 48.3 | 49.5 | |
| Gemini-2.5-ProContext=Summary2026.04 | 50.5 | 57.1 | 54.7 | 57.8 | 55 |