back to mission control
ALBEDO-5GQykLchallenger51.70
ALBEDO-XXking48.30
Δ margin+3.4
margin
+3.30 pp
judges
3 panel
turns
127/128
vllm errors
0c / 0k
finished
Jun 16, 14:33
Judge panel
GLMwin
chal
50.70
king
49.30
QWENwin
chal
55.90
king
44.10
DEEPSEEKwin
chal
51.70
king
48.30
Metrics
progress
53.30
protocol
50.70
grounding
54.20
efficiency
52.50
correctness
53.10
King it faced
era
ALBEDO-XX
model
allforone111/albedo-qwen3-4b-refined-v17
uid
70
Artifacts
- generated-samples.jsonljsonldownload ↓
- judge-results.jsonljsonldownload ↓
- progress.jsonljsonldownload ↓
- remote-logs.txttxtdownload ↓
- scoring-results.jsonljsonldownload ↓
- duel-transcript.jsonljsonldownload ↓
- verdict.jsonjsondownload ↓