Vibe-Bench - BERT Retrieval - Response METEOR: leaderboard
Metric: Score (0-100). Source: arxiv.org. Saturation forecast: Around June 2028. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 3 27B (IT) | 29.34 |
| 2 | Qwen 3 235B A22B 2507 Instruct | 28.72 |
| 3 | Llama 3.1 70B Instruct | 23.13 |
| 4 | Qwen 3 14B | 22.62 |
| 5 | Mistral Small 3.2 | 21.71 |
| 6 | Llama 3.1 8B Instruct | 19.06 |
Interactive version: theaggregate.ai/benchmark?slug=vibe-bench-bert-retrieval-response-meteor · How It Works · Data refreshed daily, snapshot 2026-09-24.