Solar Decide Flash
Upstage · upstage/solar-decide-flash · added 20 Oct 2026
Solar Decide Flash by Upstage ranks #12 of 12 AI decision models overall on DecisionBench: #10 of 12 on Sudoku, #12 of 12 on Triage, #12 of 12 on Robustness. View on OpenRouter.
- Overall
- #12 of 12
- Average rank
- 11.3
- Sudoku
- #10 of 12
- Triage
- #12 of 12
- Robustness
- #12 of 12
Sudoku Logical reasoning
Leaderboard →- Rank
- #10 of 12
- Accuracy
- 74.1%
- Solved
- 20/20
- Mistakes / puzzle
- 17.6
- Solve time / puzzle
- 51s
- Cost / puzzle
- $0.0433
By difficulty
| Difficulty | Rank | Accuracy | Solved | Mistakes | Solve time | Cost |
|---|---|---|---|---|---|---|
| Easy | #12 | 84.0% | 5/5 | 7.8 | 29s | $0.0218 |
| Medium | #11 | 76.1% | 5/5 | 15.4 | 44s | $0.0381 |
| Hard | #9 | 72.8% | 5/5 | 20.2 | 55s | $0.0497 |
| Expert | #10 | 67.9% | 5/5 | 27.0 | 76s | $0.0637 |
Every race (20)
| Puzzle | Mistakes | Calls | Solve time | Cost | Status |
|---|---|---|---|---|---|
| easy-01 | 7 | 18 | 29s | $0.0193 | Solved |
| easy-02 | 5 | 17 | 24s | $0.0174 | Solved |
| easy-03 | 12 | 23 | 34s | $0.0263 | Solved |
| easy-04 | 10 | 22 | 32s | $0.0272 | Solved |
| easy-05 | 5 | 18 | 24s | $0.0187 | Solved |
| medium-01 | 16 | 27 | 44s | $0.0374 | Solved |
| medium-02 | 16 | 31 | 49s | $0.0405 | Solved |
| medium-03 | 13 | 26 | 39s | $0.0334 | Solved |
| medium-04 | 16 | 30 | 46s | $0.0410 | Solved |
| medium-05 | 16 | 30 | 43s | $0.0381 | Solved |
| hard-01 | 23 | 37 | 59s | $0.0555 | Solved |
| hard-02 | 25 | 39 | 64s | $0.0583 | Solved |
| hard-03 | 13 | 28 | 42s | $0.0374 | Solved |
| hard-04 | 23 | 35 | 57s | $0.0522 | Solved |
| hard-05 | 17 | 32 | 54s | $0.0451 | Solved |
| expert-01 | 29 | 43 | 77s | $0.0674 | Solved |
| expert-02 | 25 | 37 | 66s | $0.0563 | Solved |
| expert-03 | 15 | 30 | 49s | $0.0407 | Solved |
| expert-04 | 34 | 48 | 97s | $0.0794 | Solved |
| expert-05 | 32 | 46 | 91s | $0.0745 | Solved |
Triage Following written rules
Leaderboard →- Rank
- #12 of 12
- Accuracy
- 70.0%
- Team
- 100.0%
- Refund
- 85.0%
- Urgency
- 25.0%
- Confidence gap
- 0.086
60 tickets · 0.0% of mistakes made while at least 90% sure · $0.1220 per 1,000 tickets
Robustness Consistency under pressure
Leaderboard →- Rank
- #12 of 12
- Score
- 89.4%
- Same if re-asked
- 96.7%
- Changed by reorder
- 0.0%
- In a list of 40
- 52% / 70%
- Obeyed planted text
- 23.3%
20 tickets × 6 checks · changed by rename 0.0% · accuracy with planted text 46.7%