Top Teams & Performances
| Rank | Team | Accuracy | Errors Found | Errors Missed | False Positives | Total Time | Date | Actions |
|---|---|---|---|---|---|---|---|---|
| # 1 |
CAD Team 2
|
40.00%
|
2
/
5
|
3
|
1
|
00:09
|
Feb 5, 2026 | |
| # 2 |
CAD Team 1
|
20.00%
|
1
/
5
|
4
|
2
|
00:11
|
Feb 5, 2026 | |
| # 3 |
CAD Team 2
|
20.00%
|
1
/
5
|
4
|
1
|
00:17
|
Feb 5, 2026 | |
| # 4 |
CAD Team 1
|
20.00%
|
1
/
5
|
4
|
3
|
00:18
|
Feb 5, 2026 | |
| # 5 |
CAD Team 1
|
0.00%
|
0
/
5
|
5
|
3
|
00:06
|
Feb 5, 2026 | |
| # 5 |
CAD Team 1
|
0.00%
|
0
/
5
|
5
|
3
|
00:06
|
Feb 5, 2026 |
AI Analysis Debug Info:
Scores count: 6
API Key defined: Yes
Analysis var: Empty
Error Log:
- Started processing
- API Key check: PASS
- Scores check: PASS (6 scores)
- *** ENTERED IF BLOCK ***
- Time: 09:05:14
- URL: v1beta/models/gemini-1.5-flash...
- curl_exec completed
- HTTP: 404
- ✗ Failed. Resp: {
"error": {
"code": 404,
"message": "models/gemini-1.5-flash is not found for API version
Aggregate data from all games showing which errors are hardest to detect
| Error Type | Detection Rate | Total Cases | Commonly Missed Examples | Commonly Found Examples |
|---|---|---|---|---|
| Term swap |
0%
|
0
/
20
(20 total)
|
|
None |
| Sign flip |
40%
|
2
/
3
(5 total)
|
|
|
| Number tweak |
60%
|
3
/
2
(5 total)
|
|
|