Skip to content

Benchmark

OmniDocBench · Score

Scores are percentages. Higher is better.

Models measured
3
Scores recorded
3
Sources
1
IQ weight
No weight published

Score distribution

89%
Mean
88.8%
Median
1.6%
Std dev
87.2%
10th percentile
91.1%
90th percentile
87.2%
Min
87.2%91.1%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Kimi K3three-run average · max effort · temp 1.0 · top_p .95· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.91.1%
2Kimi K2.5OmniDocBench 1.5· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.88.8%
3MiMo V2.5Xiaomi MiMo-V2.5 official release/model card · higher-is-better score · version unspecified· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.87.2%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.