Multimodal & Grounded benchmark
OmniDocBench 1.5 leaderboard
Every model the catalog carries a published OmniDocBench 1.5 value for, ranked by that value.
A document understanding benchmark used in frontier-model comparison tables to measure extraction and grounded reasoning quality on complex documents.
OmniDocBench 1.5 ranking
6 models with a published OmniDocBench 1.5 value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Document understanding benchmark |
|---|---|---|---|
| 1 |  Qwen3.8 Max | Alibaba | 92.1 |
| 2 |  MiniMax M3 | MiniMax | 91.6 |
| 3 | Qwen3.7 Plus | Alibaba | 91.4 |
| 4 | Qwen3.8-27B | Alibaba | 91.1 |
| 5 | Qwen3.6-35B-A3B | Alibaba | 89.9 |
| 6 |  Muse Glimmer 30B | Meta | 75.8 |
Evidence key: Observed
Rows are ordered by the value Introducing GPT-5.4 mini and nano published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.