LOM Benchmark - Summary: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-1.8-Pro | 71 |
| 2 | Qwen 3 Max | 49 |
| 3 | Qwen 3.5 27B | 22 |
| 4 | DeepSeek V3.2 | 21 |
| 5 | Qwen 3 4B Instruct | 4 |
| 6 | Qwen 2.5 32B Instruct | 0 |
| 7 | Qwen 3.5 2B | 0 |
Interactive version: theaggregate.ai/benchmark?slug=lom-benchmark-summary · How It Works · Data refreshed daily, snapshot 2026-09-05.