Diffit vs. MagicSchool
Same Prompts. Same Standards.
Two different teacher experiences.
We gave the same prompts to Diffit and MagicSchool, then scored both outputs against a 20-criterion rubric grounded in WestEd research.
3 prompts · 10 artifacts · 60+ scored criteria·May 2026
Evaluation Criteria:
- Classroom-ready & standards-aligned
- Complete & ready to teach
- Content integrity
- Differentiation that holds up
1. Classroom-ready & standards-aligned
Prompt: Adding and subtracting fractions with unlike denominators · Grade 5
Standard: CCSS.MATH.CONTENT.5.NF.A.2 — "Solve word problems involving addition and subtraction of fractions referring to the same whole, including cases of unlike denominators, e.g., by using visual fraction models or equations."
Both worksheets compute correctly and print cleanly. But MagicSchool leans on like-denominator problems (a grade-4 skill), with two "open-ended" items that are actually multiplication; it includes no visual models; and it tells students to "show your work" with nowhere to do it. Diffit targets 5.NF.A.2 directly — unlike denominators, visual fraction models, and an error-analysis task — with room to work.
Diffit
1Visual fraction models
2Unlike denominators
3Room to show work
MagicSchool
1No visual models
2Mostly like denominators
3"Show your work" — no room
2. Complete & ready to teach
Prompt: Harriet Tubman reading packet · Grade 5 · source: National Park Service
Standard: CCSS.ELA-LITERACY.RI.5.3 — "Explain the relationships or interactions between two or more individuals, events, ideas, or concepts in a historical, scientific, or technical text based on specific information in the text."
MagicSchool's worksheet is clean and complete — a passage, questions, and an answer key. But the passage is a generic paraphrase that drops the source's specifics, the questions are recall ("What year did she escape?") rather than the relationship analysis RI.5.3 asks for, and there's no image and no room to write. Diffit's packet is source-grounded, builds an interaction-analysis activity that meets the standard, and gives students space to work. (Both include answer keys.)
Diffit
1High-fidelity reading passage
2Interaction analysis (RI.5.3)
3Student answer spaces
MagicSchool
1Generic paraphrase
2Recall, not interaction
3Text only, no room to write
3. Content integrity
Prompt: MLK's "Letter from Birmingham Jail" · Grades 9–10 · source: Stanford King Institute
Standard: CCSS.ELA-LITERACY.RH.9-10.2 — "Determine the central ideas or information of a primary or secondary source; provide an accurate summary of how key events or ideas develop over the course of the text."
MagicSchool's worksheet has a passage, questions, and an answer key — but the "passage" is a ~120-word paraphrase, not King's actual letter. Every question references that paraphrase, and the answer key never quotes from the letter itself. Students summarize a summary instead of analyzing the real text RH.9-10.2 calls for. Diffit built from the source — the four-step campaign, the clergy's specific charges, King's own words — and its answer key cites the letter directly.
Diffit
1Built from the real letter
2Key quotes the letter
MagicSchool
1Built from a 120-word paraphrase
2Key never quotes the letter
4. Differentiation that holds up
Prompt: The Grade-5 Harriet Tubman packet (RI.5.3), releveled to Grade 2
Both tools translate to Spanish capably — that's a wash. The gap shows at reading level. Diffit's 2nd-grade version keeps the full story (Brodess, the dates, the Civil War service, the raid) in simpler sentences, and the same RI.5.3 analysis — how groups, places, and people shaped Tubman's life. MagicSchool's cut the passage to ~50 words and, in its own teacher note, names the standard "Verbatim Rhode Island Grade 5 Reading Standard (RI.5.3)" — RI is the Common Core code for "Reading: Informational."
Diffit · same lesson at 2nd grade
1Full story kept
2Built for RI.5.3
MagicSchool · same lesson at 2nd grade
1Cut to ~50 words
2RI = "Rhode Island"
Where Diffit fell short
We scored Diffit's own work critically, too.
It's important to note that Diffit didn't score perfectly on the rubric in a few areas, too. In the 2nd-grade rewrite, one prompt oversimplified a part of the reading; a Spanish translation used two different words for the same term ("pantanos" (swamps) in the reading passage but "marismas" (marshes) in one of the analysis activities); and the high-school lesson skipped images that may have helped with scaffolding. These are noted in the full analysis below.
The difference: a teacher can fix any of these inside Diffit in seconds — swap an image, edit a word — right in the packet. In a chatbot, that means re-prompting and hoping the rest of the lesson survives.
This isn't just our opinion
The rubric comes from research, not from us.
Both tools' materials were graded against the four things WestEd found teachers care about most: accuracy, standards alignment, ease of use, and meeting student needs — 20 criteria in all. Every score has cited evidence. All source files and the exact prompts are available upon request, so any district can rerun the comparison.
Grounded in WestEd's study, "How Teachers Judge the Quality of Instructional Materials: Selecting Instructional Materials, Brief 1 – Quality (Bugler et al., 2017)", and the Diffit Quality Constitution.
To see the full scoring, read the Diffit Quality Constitution, or learn more about Diffit, contact schools@diffit.me.