Vibe-Bench - Full History - Strategy Balanced Accuracy: leaderboard
Metric: Score (0-100). Source: arxiv.org. Saturation forecast: Around 2031. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Mistral Small 3.2 | 19.87 |
| 2 | Qwen 3 235B A22B 2507 Instruct | 18.96 |
| 3 | Llama 3.1 8B Instruct | 18.39 |
| 4 | Qwen 3 14B | 15.83 |
| 5 | Llama 3.1 70B Instruct | 15.67 |
| 6 | Gemma 3 27B (IT) | 14.48 |
Interactive version: theaggregate.ai/benchmark?slug=vibe-bench-full-history-strategy-balanced-accuracy · How It Works · Data refreshed daily, snapshot 2026-09-24.