Vibe-Bench - Personalized Fine-tuning - Strategy Macro-F1: leaderboard
Metric: Score (0-100). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen3-8B (Vibe-Bench P-SFT) | 16.52 |
| 2 | Llama-3.2-3B (Vibe-Bench P-SFT) | 10.59 |
| 3 | Llama-3.1-8B (Vibe-Bench P-SFT) | 10.14 |
| 4 | Qwen3-14B (Vibe-Bench P-SFT) | 10.08 |
| 5 | Qwen3-4B (Vibe-Bench P-SFT) | 8.1 |
| 6 | Ministral-8B (Vibe-Bench P-SFT) | 7.3 |
Interactive version: theaggregate.ai/benchmark?slug=vibe-bench-personalized-fine-tuning-strategy-macro-f1 · How It Works · Data refreshed daily, snapshot 2026-09-24.