MaMe-Re (Speech Text + Panel Description): leaderboard
Metric: Score@1 (%; mean share of five crowdworkers who rated the chosen manga-panel reply funny, 250 contexts, panels given by their speech text and a GPT-4.1 visual description). Source: arxiv.org. Saturation forecast: Around 2029. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 32.5 |
| 2 | GPT-5 Mini | 30 |
| 3 | Gemini 2.5 Pro | 29.4 |
| 4 | GPT-OSS-120B | 28.4 |
| 5 | Gemini 2.5 Flash | 27.6 |
| 6 | Claude Sonnet 4 (20250514) | 26.1 |
Interactive version: theaggregate.ai/benchmark?slug=mame-re-speech-text-plus-panel-description · How It Works · Data refreshed daily, snapshot 2026-09-25.