Generator Factual Competence on Criterion A 285 instantiations
7GF Scoreclaude-opus-4.5
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| claude-opus-4.52026.06 | 7 | — | |
| claude-opus-4.02026.06 | 6.98 | 6.93 | |
| claude-sonnet-42026.06 | 6.98 | 6.95 | |
| claude-opus-4.12026.06 | 6.97 | 6.89 | |
| gemini-2.5-flash2026.06 | 6.63 | 6.44 | |
| gemini-3.1-pro2026.06 | 6.58 | 6.35 | |
| gpt-4.1-2025-04-142026.06 | 6.49 | 6.26 | |
| gpt-4.1-mini2026.06 | 6.27 | 6.02 | |
| gpt-4o-2024-08-062026.06 | 5.21 | 5.02 | |
| gpt-4o2026.06 | 5.11 | 4.88 | |
| gpt-4.1-nano2026.06 | 3.65 | 3.19 | |
| gpt-4o-mini2026.06 | 3.19 | 2.79 |