back to mission control
ALBEDO-5GhJjfchallenger55.70
ALBEDO-XXXking44.30
Δ margin+11.4
margin
+11.30 pp
judges
3 panel
turns
127/128
vllm errors
0c / 0k
finished
Jun 17, 04:06
Judge panel
GLMwin
chal
55.70
king
44.30
QWENwin
chal
59.00
king
41.00
DEEPSEEKwin
chal
53.60
king
46.40
Metrics
progress
58.50
protocol
51.30
grounding
55.50
efficiency
58.50
correctness
56.60
King it faced
era
ALBEDO-XXX
model
allforone1l1/albedo-qwen3-4b-test
uid
161
Artifacts
- generated-samples.jsonljsonldownload ↓
- judge-results.jsonljsonldownload ↓
- progress.jsonljsonldownload ↓
- remote-logs.txttxtdownload ↓
- scoring-results.jsonljsonldownload ↓
- duel-transcript.jsonljsonldownload ↓
- verdict.jsonjsondownload ↓