SenseBench - Paired-Image Description: leaderboard
Metric: Judge Score Sum (0-6; Prometheus completeness, correctness and faithfulness against the verified reference report, 0-2 each, image pairs). Source: arxiv.org. Saturation forecast: Around May 2027. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 4.69 |
| 2 | Qwen 3.5 Plus | 4.5 |
| 3 | GPT-5.4 | 4.1 |
| 4 | Qwen 3 VL 8B | 3.13 |
Interactive version: theaggregate.ai/benchmark?slug=sensebench-paired-image-description · How It Works · Data refreshed daily, snapshot 2026-09-25.