0–1
Thesis / claim
A historically defensible line of reasoning that responds to the prompt, on both the DBQ and LEQ.
AP World History
Grade your AP World essay
DBQ or LEQ, covering world history from 1200 CE to today. Paste your draft into this free essay grader, add your documents for a DBQ, and get a score against the real four-category rubric in under 30 seconds.
how it's scored
The DBQ and LEQ share the same four categories. The DBQ adds a third evidence point for outside documents and is worth 7 points total; the LEQ tops out at 6.
The four categories are the same across AP US, European, and World History. The DBQ adds document sourcing and a higher evidence ceiling.
| Category | DBQ | LEQ | What readers check |
|---|---|---|---|
| Thesis / claim | 1 pt | 1 pt | Historically defensible line of reasoning |
| Contextualization | 1 pt | 1 pt | Broader historical situation beyond the prompt |
| Evidence | Up to 3 pts | Up to 2 pts | DBQ: 3+ then 6+ documents plus outside evidence; LEQ: specific facts used to argue |
| Analysis and reasoning | Up to 2 pts | Up to 2 pts | DBQ: sourcing 3+ documents plus complexity; LEQ: reasoning skill plus complexity |
| Total | 7 pts | 6 pts | Same rubric logic; DBQ adds document mechanics |
0–1
Contextualization
A broader historical situation beyond the prompt's immediate timeframe, not a second thesis sentence.
0–3 (DBQ) / 0–2 (LEQ)
Evidence
DBQ: using 3+ documents, then 6+ to support an argument, then one piece of outside evidence. LEQ: specific evidence used to support an argument.
0–2
Analysis and reasoning
DBQ: sourcing at least 3 documents, plus complexity. LEQ: a historical reasoning skill (comparison, causation, or continuity/change), plus complexity.
Total: 7 (DBQ) / 6 (LEQ) points
For a DBQ on the Columbian Exchange, a strong contextualization sentence frames the preceding Mongol-era trade networks that already connected Afro-Eurasia before 1492.
no nonsense numbers
you need something you can trust. not just ChatGPT.
Accuracy
93.9%
of our grades within 1 point
of a real AP score
Agreement
0.84
average QWK*
across 98 human-graded essays
Precision
0.55
average MAE**
points off vs human scores
across 98 human-graded essays
Volume
essays graded
and counting
* QWK (Quadratic Weighted Kappa) measures how closely our scores match human AP graders. Our average QWK is 0.84 across 98 human-graded AP essays. Learnosity classifies 0.80+ as almost perfect agreement. Read more about our benchmarks.
** MAE (Mean Absolute Error) is the average number of points our total score differs from a human AP score. Our average MAE is 0.55 points across 98 human-graded AP essays. Lower is better.
These aggregate numbers were validated on AP History Long Essay (LEQ) essays; accuracy has not yet been separately validated for the DBQ, which scores an additional evidence category.
