Qwen3.8 Flash-Next
Alibaba · open weights · released 2026-08-26 · route qwen3.8-flash-next · Model profile · Chess results
Results
- Score
- 4895%: 35 to 60
- Grids solved
- 20 of 42
- Blank cells filled correctly
- 45.8%
- Wrong cells / empty cells / changed a given / no grid
- 0 / 0 / 0 / 22
- Broke the rules (complete grid repeating a digit)
- 0
- Near misses (three cells or fewer wrong)
- 0
- Average stated confidence
- 100%
- Average confidence when it had not solved it
- n/a
- Sure but wrong (90% or more, unsolved)
- 0
- Calibration (Brier, lower is better)
- 0.000
- API-equivalent cost per grid
- n/a
- API-equivalent cost per solved grid
- n/a
- Seconds per grid
- 3,442
- Tokens per grid (in / out)
- 609 / 65,074
- Reasoning tokens per grid
- n/a
- Retries for an unreadable reply
- 27
- Aborted on our side (not counted)
- 499
By tier
| Tier | Needs | Solved | Output tokens | Seconds |
|---|---|---|---|---|
| Cozy | Singles only | 4 of 6 | 34,346 | 1,653 |
| Gentle | Scanning | 4 of 6 | 50,644 | 2,629 |
| Steady | Locked candidates | 2 of 6 | 81,530 | 4,217 |
| Tricky | Hidden pairs and triples | 2 of 6 | 80,861 | 4,825 |
| Devious | Wings and fish | 4 of 6 | 50,950 | 2,584 |
| Expert | Deep wings and fish | 4 of 6 | 65,709 | 3,406 |
| Beyond | No human technique finishes it | 0 of 6 | 91,478 | 4,783 |
Cells by the technique they needed
Each blank cell is tagged with the simplest technique that fills it, given everything a solver could fill before it.
| Technique | Cells | Filled correctly |
|---|---|---|
| Last free cell | 274 | 100.0% |
| Scanning | 385 | 100.0% |
| Locked candidates | 78 | 100.0% |
| Hidden pairs and triples | 80 | 100.0% |
| Wings and fish | 99 | 100.0% |
| Deep wings and fish | 106 | 100.0% |
Every answer
Cozy #1No readable grid 0 of 50 cells83,556 tokens · localCozy #2Solved 48 of 48 cells100% sure · 14,860 tokens · localCozy #3Solved 49 of 49 cells100% sure · 13,547 tokens · localCozy #4No readable grid 0 of 50 cells73,225 tokens · localCozy #5Solved 49 of 49 cells100% sure · 10,102 tokens · localCozy #6Solved 39 of 39 cells100% sure · 10,785 tokens · localGentle #1Solved 56 of 56 cells100% sure · 70,352 tokens · localGentle #2Solved 51 of 51 cells100% sure · 15,630 tokens · localGentle #3Solved 52 of 52 cells100% sure · 23,580 tokens · localGentle #4No readable grid 0 of 51 cells94,373 tokens · localGentle #5No readable grid 0 of 56 cells83,341 tokens · localGentle #6Solved 52 of 52 cells100% sure · 16,586 tokens · localSteady #1No readable grid 0 of 53 cells100,216 tokens · localSteady #2Solved 53 of 53 cells100% sure · 89,458 tokens · localSteady #3No readable grid 0 of 49 cells84,106 tokens · localSteady #4No readable grid 0 of 54 cells103,188 tokens · localSteady #5Solved 53 of 53 cells100% sure · 19,960 tokens · localSteady #6No readable grid 0 of 54 cells92,249 tokens · localTricky #1Solved 55 of 55 cells100% sure · 22,139 tokens · localTricky #2No readable grid 0 of 57 cells103,213 tokens · localTricky #3No readable grid 0 of 57 cells91,670 tokens · localTricky #4No readable grid 0 of 54 cells85,975 tokens · localTricky #5Solved 55 of 55 cells100% sure · 87,346 tokens · localTricky #6No readable grid 0 of 56 cells94,824 tokens · localDevious #1Solved 55 of 55 cells100% sure · 35,979 tokens · localDevious #2No readable grid 0 of 55 cells98,063 tokens · localDevious #3Solved 49 of 49 cells100% sure · 27,992 tokens · localDevious #4Solved 40 of 40 cells100% sure · 11,082 tokens · localDevious #5Solved 47 of 47 cells100% sure · 35,422 tokens · localDevious #6No readable grid 0 of 54 cells97,164 tokens · localExpert #1No readable grid 0 of 58 cells92,340 tokens · localExpert #2Solved 53 of 53 cells100% sure · 58,312 tokens · localExpert #3Solved 54 of 54 cells100% sure · 41,640 tokens · localExpert #4No readable grid 0 of 57 cells85,456 tokens · localExpert #5Solved 58 of 58 cells100% sure · 91,262 tokens · localExpert #6Solved 54 of 54 cells100% sure · 25,245 tokens · localBeyond #1No readable grid 0 of 60 cells101,374 tokens · localBeyond #2No readable grid 0 of 57 cells87,683 tokens · localBeyond #3No readable grid 0 of 56 cells94,025 tokens · localBeyond #4No readable grid 0 of 57 cells77,557 tokens · localBeyond #5No readable grid 0 of 59 cells100,283 tokens · localBeyond #6No readable grid 0 of 57 cells87,946 tokens · local