Benchmarks

Academi.cx vs Originality AI

We benchmarked Academi.cx and Originality AI against Turnitin across 429 documents, measuring score differences, false flags, and missed AI.

Brayden · 2 min read

For this benchmark, we submitted the same 429 documents to Academi.cx and Originality AI through their APIs, then compared each tool’s scores with the documents’ actual Turnitin AI scores. Together those documents add up to close to 944,000 words, averaging about 2,200 words each, ranging from a 311 word short answer to a 25,000 word thesis.

How close were the predictions

Across all 429 documents, Academi.cx averaged 1.92 points off the real Turnitin score. Originality AI averaged 12.93 points off. Its median error sits at 5.0, meaning even a typical prediction was off by five points before accounting for its bigger misses.

Paired scatterplots show the AI score for all 429 matched documents against Turnitin. Academi.cx appears in blue and Originality AI in gray, with identical 0 to 100 percent axes. The dashed diagonal marks matching scores. Mean absolute difference from Turnitin is 1.92 percentage points for Academi.cx and 12.93 for Originality AI. No documents are omitted; some points overlap.

Breaking it down by document type

The 429 documents split into 220 that Turnitin scored as 0% AI, 99 it scored as 100% AI, and 110 that fell somewhere in between.

Grouped bars show average absolute deviation from Turnitin in percentage points. All documents (n = 429): Academi.cx 1.92 points and Originality AI 12.93 points. Turnitin 0% (n = 220): Academi.cx 0.18 points and Originality AI 14.48 points. Turnitin 20–99% (n = 110): Academi.cx 3.95 points and Originality AI 17.11 points. Turnitin 100% (n = 99): Academi.cx 3.53 points and Originality AI 4.85 points. Blue represents Academi.cx and gray Originality AI. Lower is better. All bars share a 0 to 40 point scale.

Originality AI's worst number shows up on the 0% documents, the ones that should be the easiest call. It averaged 14.48 points of error there against Academi.cx's 0.18. On the 100% documents it closed the gap some, averaging 4.85 points off versus Academi.cx's 3.53, its best relative showing of the three groups. In the mixed bucket it climbed back up to 17.11 against Academi.cx's 3.95.

False flags and missed AI

Academi.cx had a 0% false flag rate and a 0% missed AI rate across all 429 documents, meaning it never scored a genuinely 0% document above 20%, and never scored a genuinely 100% document below 80%. Originality AI came in at a 24.1% false flag rate, the highest of any tool covered in this entire benchmark, meaning close to a quarter of genuinely human written documents scored above 20% AI on Originality AI. Its missed AI rate was 7.1%.

Sentence level accuracy

We also checked how often each tool correctly classified individual sentences as AI written or human written, matched against Turnitin's own sentence level calls. Across all 429 documents, Academi.cx correctly classified 96.64% of sentences. Originality AI came in at 75.79%.

The takeaway

Across all 429 documents, Academi.cx stayed close to the actual Turnitin percentage on every measure checked. Originality AI's standout weakness was its false flag rate, the highest of any tool in this benchmark, wrongly flagging genuinely human writing more often than any other detector tested.

See the full benchmark results.

Related reading