LVBench — leaderboard
LVBench evaluates model capability on multimodal tasks from the linked upstream source with Score as the primary reported metric.
Metric: Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 27 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 77.4 |
| 2 | Qwen 3.7 Plus | 76.2 |
| 3 | Gemini 3.1 Pro (Preview) | 75.1 |
| 4 | Qwen 3.6 Plus | 74.8 |
| 5 | Claude Opus 4.6 (Max) | 63 |
| 6 | GPT-4o (2024-11-20) | 48.9 |
| 7 | InternVL2.5-78B | 43.6 |
| 8 | Qwen 2 VL 72B | 41.3 |
| 9 | Gemini 1.5 Pro | 33.1 |
| 10 | GPT-4o (2024-05-13) | 30.8 |
| 11 | GPT-4o | 27 |
Interactive version: theaggregate.ai/benchmark?slug=lvbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.