d1
Liquid · liquid/d1 · added 20 Oct 2026
d1 by Liquid ranks #7 of 12 AI decision models overall on DecisionBench: #4 of 12 on Sudoku, #7 of 12 on Triage, #8 of 12 on Robustness. View on OpenRouter.
- Overall
- #7 of 12
- Average rank
- 6.3
- Sudoku
- #4 of 12
- Triage
- #7 of 12
- Robustness
- #8 of 12
Sudoku Logical reasoning
Leaderboard →- Rank
- #4 of 12
- Accuracy
- 81.5%
- Solved
- 20/20
- Mistakes / puzzle
- 11.4
- Solve time / puzzle
- 9.5s
- Cost / puzzle
- $0.001373
By difficulty
| Difficulty | Rank | Accuracy | Solved | Mistakes | Solve time | Cost |
|---|---|---|---|---|---|---|
| Easy | #2 | 91.1% | 5/5 | 4.0 | 7.3s | $0.000750 |
| Medium | #1 | 85.1% | 5/5 | 8.6 | 9.4s | $0.001211 |
| Hard | #5 | 78.0% | 5/5 | 15.2 | 10s | $0.001680 |
| Expert | #3 | 76.3% | 5/5 | 17.8 | 11s | $0.001852 |
Every race (20)
| Puzzle | Mistakes | Calls | Solve time | Cost | Status |
|---|---|---|---|---|---|
| easy-01 | 3 | 15 | 7.5s | $0.000671 | Solved |
| easy-02 | 2 | 16 | 5.9s | $0.000685 | Solved |
| easy-03 | 5 | 17 | 6.9s | $0.000815 | Solved |
| easy-04 | 7 | 18 | 10s | $0.000881 | Solved |
| easy-05 | 3 | 15 | 6.1s | $0.000698 | Solved |
| medium-01 | 7 | 22 | 9.1s | $0.001147 | Solved |
| medium-02 | 8 | 23 | 9.6s | $0.001235 | Solved |
| medium-03 | 9 | 23 | 9.7s | $0.001279 | Solved |
| medium-04 | 7 | 22 | 10s | $0.001197 | Solved |
| medium-05 | 12 | 23 | 8.0s | $0.001201 | Solved |
| hard-01 | 17 | 30 | 15s | $0.001774 | Solved |
| hard-02 | 13 | 27 | 9.1s | $0.001507 | Solved |
| hard-03 | 10 | 26 | 7.3s | $0.001350 | Solved |
| hard-04 | 15 | 29 | 9.5s | $0.001705 | Solved |
| hard-05 | 21 | 33 | 10s | $0.002065 | Solved |
| expert-01 | 21 | 34 | 11s | $0.001963 | Solved |
| expert-02 | 12 | 27 | 9.8s | $0.001566 | Solved |
| expert-03 | 21 | 34 | 12s | $0.001919 | Solved |
| expert-04 | 15 | 31 | 11s | $0.001879 | Solved |
| expert-05 | 20 | 32 | 11s | $0.001933 | Solved |
Triage Following written rules
Leaderboard →- Rank
- #7 of 12
- Accuracy
- 93.9%
- Team
- 100.0%
- Refund
- 100.0%
- Urgency
- 81.7%
- Confidence gap
- 0.038
60 tickets · 0.0% of mistakes made while at least 90% sure · $0.0138 per 1,000 tickets
Robustness Consistency under pressure
Leaderboard →- Rank
- #8 of 12
- Score
- 97.8%
- Same if re-asked
- 94.2%
- Changed by reorder
- 0.0%
- In a list of 40
- 92% / 95%
- Obeyed planted text
- 1.7%
20 tickets × 6 checks · changed by rename 0.0% · accuracy with planted text 90.0%