Fucc Boi Bench: leaderboard
Model-judged behaviour benchmark by Patrick Lee: 41 models each reply to 96 English dating-message requests in eight families such as flirting, honesty, consent, breadcrumbing and accountability. A GLM 5.3 judge grades honesty, clarity and respect; each reply scores 0-10 with extra points for serious misses like ignoring a clear no, and the board is a model's mean. Lower is better; scores track refusal rate closely.
Metric: Average Fuccboi Score (0-10, lower is better). Source: huggingface.co. Saturation forecast: Around June 2028. 41 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5 | 2.02 | #16 |
| 2 | GPT-6 Astra | 2.2 | #6 |
| 3 | GPT-5.6 Sol | 2.66 | #22 |
| 4 | Claude Fable 5.1 | 3.48 | #10 |
| 5 | GLM-5.3 | 3.8 | #44 |
| 6 | Claude Sonnet 4 | 3.83 | #207 |
| 7 | Claude Fable 5 | 3.93 | #20 |
| 8 | Inkling | 3.94 | #144 |
| 9 | Kimi K3 | 3.95 | #35 |
| 10 | GPT-5.6 Luna | 4.38 | #79 |
| 11 | Muse Glimmer 30B | 4.73 | #191 |
| 12 | MiMo-V2.5-Pro | 5.12 | #167 |
| 13 | Nemotron 3 Ultra | 5.2 | #245 |
| 14 | Hy4 preview | 5.5 | #45 |
| 15 | MiniMax-M3 | 5.72 | #151 |
No result here: #3 Claude Opus 5.5, #7 GPT-6.1 Sol, #9 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=fucc-boi-bench · How It Works · Data refreshed daily, snapshot 2026-11-05.