Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

Office Comprehension Bench - File Fidelity Word — leaderboard

Metric: File Fidelity Accuracy (%). Source: arxiv.org. 4 models tracked.

Top models

#ModelScore
1Claude Opus 4.791.5
2Median Human78.6
3Gemini 3.1 Pro (Preview)55.3

Interactive version: theaggregate.ai/benchmark?slug=office-comprehension-bench-file-fidelity-word · How the rankings work · Data refreshed daily, snapshot 2026-07-22.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.