back to mission control
ALBEDO-5H6GLLchallenger54.80
ALBEDO-XVIIking45.20
Δ margin+9.6
margin
+9.50 pp
judges
3 panel
turns
128/128
vllm errors
0c / 0k
finished
Jun 16, 10:47
Judge panel
GLMwin
chal
54.10
king
45.90
QWENwin
chal
54.80
king
45.20
DEEPSEEKwin
chal
56.00
king
44.00
Metrics
progress
57.00
protocol
49.10
grounding
56.10
efficiency
55.70
correctness
56.90
King it faced
era
ALBEDO-XVII
model
superstar/albedo-qwen3-4b-v1
uid
118
Artifacts
- generated-samples.jsonljsonldownload ↓
- judge-results.jsonljsonldownload ↓
- progress.jsonljsonldownload ↓
- remote-logs.txttxtdownload ↓
- scoring-results.jsonljsonldownload ↓
- duel-transcript.jsonljsonldownload ↓
- verdict.jsonjsondownload ↓