Evaluator Factual Competence on Criterion A 285 instantiations
0.58EF Loadinggemini-3.1-pro
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| gemini-3.1-pro2026.06 | 0.58 | 7.36 | 7.16 | |
| claude-opus-4.52026.06 | 0.55 | 7 | 7 | |
| gemini-2.5-flash2026.06 | 0.36 | 4.68 | 3.58 | |
| claude-opus-4.02026.06 | 0.35 | 4.47 | 3.97 | |
| claude-opus-4.12026.06 | 0.28 | 3.55 | 3.33 | |
| claude-sonnet-42026.06 | 0.13 | 1.62 | 1.43 | |
| gpt-4.1-mini2026.06 | 0.09 | 1.21 | 0.4 | |
| gpt-4o-2024-08-062026.06 | 0.05 | 0.62 | 0.25 | |
| gpt-4.1-nano2026.06 | 0.04 | 0.49 | 0.13 | |
| gpt-4o2026.06 | 0.03 | 0.34 | 0.08 | |
| gpt-4.1-2025-04-142026.06 | 0.02 | 0.2 | 0.14 | |
| gpt-4o-mini2026.06 | 0 | 0 | 0 |