Skip to content
decisionbench
OverallSudokuRulebookConsistencyOdds

Independent benchmark. Not affiliated with or endorsed by OpenRouter or any model provider. Company and model names are trademarks of their respective owners.

How ranking worksPrivacyTermsContact

© 2026 editid0

← Rulebook leaderboard

Drex v2.0

Nace.AI · nace-ai/drex-v2.0 · added 20 Oct 2026

Older version: Drex v1.5

Drex v2.0 by Nace.AI ranks #6 of 17 AI decision models on the DecisionBench Rulebook benchmark (following written rules), with accuracy 96.1%. View on OpenRouter.

Overall#5Sudoku#6Rulebook#6Consistency#3Odds#13
Rulebook rank
#6 of 17
Accuracy
96.1%
Team
100.0%
Refund
96.7%
Urgency
91.7%
Confidence gap
0.030

60 tickets · 0.0% of mistakes made while at least 90% sure · $0.0364 per 1,000 tickets · 464 ms per ticket

Every ticket

The model's three decisions on each ticket, with its confidence. Wrong answers show the right one. 7 of 60 tickets had at least one mistake.

TicketCustomer wroteTeamRefundUrgency
T-1000My invoice says $425 but checkout showed $405. Why was I charged more?✓ billing 100%✓ approve 99%✓ 1 96%
T-1001Tracking says delivered but there is nothing at my door or with my neighbours.✓ shipping 99%✓ deny 97%✓ 1 96%
T-1002I changed my mind about order #468974 and want to return it.✓ returns 100%✓ deny 100%✓ 2 93%
T-1003Sync stops halfway through and shows error E-883.✓ technical 100%✓ deny 93%✓ 1 95%
T-1004Someone changed the email on my account without my permission.✓ fraud 97%✓ deny 79%✓ 0 99%
T-1005My card was billed again after I cancelled. Can you look into this charge?✓ billing 99%✓ deny 90%✓ 1 96%
T-1006My package for order #822804 hasn't arrived and tracking hasn't moved in 7 days.✓ shipping 100%✓ approve 99%✓ 2 86%
T-1007I changed my mind about order #797563 and want to return it.✓ returns 100%✓ approve 99%✓ 1 86%
T-1008The app crashes every time I open the settings page.✓ technical 100%✓ deny 99%✓ 1 95%
T-1009Someone changed the email on my account without my permission.✓ fraud 96%✓ deny 93%✓ 3 94%
T-1010My card was billed again after I cancelled. Can you look into this charge?✓ billing 99%✓ approve 97%✓ 1 94%
T-1011The courier sent order #441011 to my old address instead of the one I entered.✓ shipping 99%✓ approve 99%✓ 2 87%
T-1012I bought the wrong plan by mistake and want to undo the purchase.✓ returns 98%✓ approve 97%✓ 2 85%
T-1013Export to PDF has been broken since the last update.✓ fraud 99%✓ deny 90%✓ 1 87%
T-1014Someone changed the email on my account without my permission.✓ fraud 97%✓ deny 81%✓ 1 96%
T-1015My invoice says $62 but checkout showed $42. Why was I charged more?✓ billing 100%✓ deny 100%✓ 2 89%
T-1016My package for order #455490 hasn't arrived and tracking hasn't moved in 4 days.✓ fraud 100%✓ deny 96%✓ 1 64%
T-1017I bought the wrong plan by mistake and want to undo the purchase.✓ returns 99%✓ approve 97%✓ 1 94%
T-1018Export to PDF has been broken since the last update.✓ fraud 99%✓ deny 88%✓ 1 90%
T-1019Someone changed the email on my account without my permission.✓ fraud 100%✓ deny 93%✕ 2 → 1 75%
T-1020I was charged twice for order #227551. Please fix the duplicate charge.✓ fraud 99%✓ deny 70%✓ 2 81%
T-1021My package for order #718743 hasn't arrived and tracking hasn't moved in 8 days.✓ shipping 100%✓ approve 99%✓ 3 90%
T-1022I bought the wrong plan by mistake and want to undo the purchase.✓ returns 99%✓ deny 97%✕ 3 → 4 88%
T-1023Export to PDF has been broken since the last update.✓ technical 100%✓ deny 75%✓ 2 89%
T-1024I got a login alert from a country I've never been to.✓ fraud 89%✓ deny 77%✓ 2 91%
T-1025My invoice says $261 but checkout showed $241. Why was I charged more?✓ billing 100%✓ approve 99%✓ 1 97%
T-1026My package for order #821430 hasn't arrived and tracking hasn't moved in 10 days.✓ shipping 100%✓ approve 98%✓ 0 99%
T-1027I bought the wrong plan by mistake and want to undo the purchase.✓ returns 99%✓ approve 96%✓ 0 99%
T-1028The app crashes every time I open the settings page.✓ technical 100%✓ deny 99%✓ 3 91%
T-1029Someone changed the email on my account without my permission.✓ fraud 98%✓ deny 73%✓ 2 86%
T-1030My card was billed again after I cancelled. Can you look into this charge?✓ billing 99%✓ approve 96%✓ 1 89%
T-1031The courier sent order #259717 to my old address instead of the one I entered.✓ shipping 99%✓ approve 99%✓ 1 92%
T-1032I bought the wrong plan by mistake and want to undo the purchase.✓ returns 99%✓ approve 97%✓ 2 82%
T-1033Export to PDF has been broken since the last update.✓ technical 100%✓ deny 92%✓ 3 94%
T-1034There's an order #135622 on my account that I did not place.✓ fraud 100%✓ deny 72%✕ 3 → 4 84%
T-1035My card was billed again after I cancelled. Can you look into this charge?✓ billing 99%✓ approve 97%✓ 1 95%
T-1036Tracking says delivered but there is nothing at my door or with my neighbours.✓ shipping 99%✓ approve 99%✓ 0 99%
T-1037You sent me the wrong colour. How do I return it?✓ returns 100%✓ deny 96%✓ 2 93%
T-1038I can't log in. It keeps saying "session expired" even after resetting my password.✓ technical 100%✓ deny 96%✓ 1 94%
T-1039There's an order #919845 on my account that I did not place.✓ fraud 92%✕ approve → deny 70%✓ 0 99%
T-1040My invoice says $72 but checkout showed $52. Why was I charged more?✓ billing 100%✓ deny 100%✓ 2 93%
T-1041My package for order #643805 hasn't arrived and tracking hasn't moved in 9 days.✓ shipping 100%✓ deny 99%✓ 0 99%
T-1042I bought the wrong plan by mistake and want to undo the purchase.✓ returns 99%✓ deny 98%✓ 1 94%
T-1043Sync stops halfway through and shows error E-132.✓ technical 100%✓ deny 97%✓ 0 99%
T-1044I got a login alert from a country I've never been to.✓ fraud 91%✓ deny 98%✓ 1 93%
T-1045My invoice says $377 but checkout showed $357. Why was I charged more?✓ billing 100%✓ approve 98%✕ 3 → 2 88%
T-1046Tracking says delivered but there is nothing at my door or with my neighbours.✓ fraud 99%✓ deny 85%✓ 3 91%
T-1047You sent me the wrong colour. How do I return it?✓ returns 100%✓ deny 99%✓ 1 98%
T-1048Export to PDF has been broken since the last update.✓ fraud 100%✓ deny 89%✓ 1 86%
T-1049There's an order #917499 on my account that I did not place.✓ fraud 85%✓ deny 94%✓ 1 97%
T-1050I was charged twice for order #334980. Please fix the duplicate charge.✓ billing 99%✓ approve 94%✕ 3 → 4 84%
T-1051Tracking says delivered but there is nothing at my door or with my neighbours.✓ shipping 99%✓ approve 99%✓ 3 90%
T-1052I bought the wrong plan by mistake and want to undo the purchase.✓ returns 99%✓ deny 100%✓ 2 86%
T-1053Sync stops halfway through and shows error E-508.✓ technical 100%✓ deny 82%✓ 0 99%
T-1054Someone changed the email on my account without my permission.✓ fraud 96%✓ deny 83%✓ 0 100%
T-1055My card was billed again after I cancelled. Can you look into this charge?✓ billing 99%✓ approve 98%✓ 3 91%
T-1056The courier sent order #983082 to my old address instead of the one I entered.✓ shipping 100%✓ approve 96%✓ 1 95%
T-1057I bought the wrong plan by mistake and want to undo the purchase.✓ returns 99%✓ approve 98%✓ 2 89%
T-1058The app crashes every time I open the settings page.✓ technical 100%✓ deny 96%✓ 0 99%
T-1059There's an order #230179 on my account that I did not place.✓ fraud 87%✕ approve → deny 88%✓ 2 92%

Percentages are the model's own confidence. Every rule is on the Rulebook page.

Drex v2.0 across all benchmarks · How Rulebook works