back to mission control
ALBEDO-5CtnUPchallenger47.60
ALBEDO-XXXIking52.40
Δ margin-4.8
margin
-4.80 pp
judges
3 panel
turns
128/128
vllm errors
0c / 0k
finished
Jun 17, 04:46
Judge panel
GLMlose
chal
47.10
king
52.90
QWENlose
chal
48.40
king
51.60
DEEPSEEKlose
chal
47.60
king
52.40
Metrics
progress
47.30
protocol
51.00
grounding
45.70
efficiency
47.40
correctness
47.10
King it faced
era
ALBEDO-XXXI
model
divinequest/albedo-qwen3-4b-2f6c8cc7
uid
215
Artifacts
- generated-samples.jsonljsonldownload ↓
- judge-results.jsonljsonldownload ↓
- progress.jsonljsonldownload ↓
- remote-logs.txttxtdownload ↓
- scoring-results.jsonljsonldownload ↓
- duel-transcript.jsonljsonldownload ↓
- verdict.jsonjsondownload ↓