Phun-Bench - Rhyming Sentence Generation (2-Rhyme): leaderboard
Metric: Exact-match rate (%) of the rhyme groups of the generated sentence's last two characters with the reference lyric line (1,000 lines; copying the reference ending disqualifies); thinking models run on 300 sampled items per setting, DeepSeek-V3 and GPT-4o on 500, the others on the full set; recommended sampling temperatures; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek R1 0528 | 84.8 |
| 2 | DeepSeek V3 (0324) | 8.3 |
| 3 | GPT-4o (2024-11-20) | 7.2 |
| 4 | Qwen 3 8B (Non-reasoning) | 5.1 |
| 5 | Llama 3.2 3B Instruct | 1.4 |
| 6 | GLM-4 9B Chat | 0.9 |
Interactive version: theaggregate.ai/benchmark?slug=phun-bench-rhyming-sentence-generation-2-rhyme · How It Works · Data refreshed daily, snapshot 2026-09-29.