ShellfishNet Captioning: leaderboard
Metric: BERTScore F1 (0-100; the paper's 0-1 score times 100) of the model caption against expert-reviewed reference captions covering morphology, color and texture, anatomical features and environment, on the 500-image ShellfishNet captioning subset (32 shellfish taxa in field, aquaculture and market scenes); higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 90.06 |
| 2 | GPT-5.4 | 88.8 |
| 3 | Qwen 2.5 VL 7B Instruct | 87.5 |
| 4 | InternVL2-8B | 86.15 |
| 5 | Qwen 2 VL 7B | 85.93 |
| 6 | Qwen 2 VL 2B | 85.15 |
Interactive version: theaggregate.ai/benchmark?slug=shellfishnet-captioning · How It Works · Data refreshed daily, snapshot 2026-10-07.