AI exam result · HISTORICAL
gemini-3.6-flash · video annotation
42.11/100 · Did not pass. One recorded attempt.
Campaign coverage
1 of 1 planned attempts recorded. All planned attempts are recorded.
Video · gemini-3.6-flash
42.11/100 · Grader quality score
1 attempts; 0 passed; 1 failed. Quality measures answer accuracy; passing also requires the exam’s declared minimums.
Input: native video file; provider-side sampling is not independently observed.
| Measure | Score |
|---|---|
| Classification accuracy | 1.00 |
| Event matching (F1) | 0.50 |
| Segment matching (F1) | 1.00 |
| Box matching (F1) | 0.00 |
| Track consistency on matched boxes | 0.00 |
What this result establishes
- This is one attempt on one fixed video task, not a general model ranking or a reliable success rate.
- The input delivery is recorded; the provider’s internal video processing is not independently observable.
- This record does not include independent human validation of the reference answers.
Technical evidence and detailed report
Detailed technical report (PDF) · Results and record digests (JSON) · Attempt counts and commitments (JSON)
These optional files provide the full audit detail behind this result.
fc-2917108cf6be