Skip to content

Benchmark

OmniDocBench 1.5

Scores are percentages.

Models measured
19
Scores recorded
19
Sources
1
IQ weight
0.47

Score distribution

67.9%
Mean
88.8%
Median
33.5%
Std dev
11.5%
10th percentile
91.2%
90th percentile
10.6%
Min
10.6%91.6%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.47 for chat models, measured over 19 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1MiniMax M3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.6%
2Qwen3.7 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.4%
3Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.2%
4Qwen 3.8 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.1%
5Qwen3.6 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.9%
6Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.8%
7Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.3%
8GPT 5.4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.1%
9Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88.9%
10Kimi K2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88.8%
11GPT-5.5 Instant· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.5%
12GPT-5.4 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.4%
13GPT 5.4 Nano· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim75.8%
14Muse Glimmer 30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim75.8%
15Gemma 4 12B It· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim16.4%
16Gemini 3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim12.1%
17Gemini 3 Pro Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim11.5%
18Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim11%
19Doubao Seed 1.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim10.6%

Data credits: Data by LLM Stats