back to mission control
ALBEDO-5CZmNuchallenger53.30
ALBEDO-XXVIking46.70
Δ margin+6.6
margin
+6.70 pp
judges
3 panel
turns
126/128
vllm errors
0c / 0k
finished
Jun 16, 21:04
Judge panel
GLMwin
chal
53.30
king
46.70
QWENwin
chal
59.20
king
40.80
DEEPSEEKlose
chal
47.90
king
52.10
Metrics
progress
54.20
protocol
52.20
grounding
52.00
efficiency
53.80
correctness
55.20
King it faced
era
ALBEDO-XXVI
model
acdc/albedo-qwen3-4b-k7p4m2
uid
252
Artifacts
- generated-samples.jsonljsonldownload ↓
- judge-results.jsonljsonldownload ↓
- progress.jsonljsonldownload ↓
- remote-logs.txttxtdownload ↓
- scoring-results.jsonljsonldownload ↓
- duel-transcript.jsonljsonldownload ↓
- verdict.jsonjsondownload ↓