back to mission control
ALBEDO-5H1F3Dchallenger48.40
ALBEDO-XXIXking51.60
Δ margin-3.2
margin
-3.10 pp
judges
3 panel
turns
128/128
vllm errors
0c / 0k
finished
Jun 17, 00:02
Judge panel
GLMlose
chal
48.40
king
51.60
QWENwin
chal
51.60
king
48.40
DEEPSEEKlose
chal
46.90
king
53.10
Metrics
progress
48.30
protocol
49.10
grounding
49.20
efficiency
49.20
correctness
49.00
King it faced
era
ALBEDO-XXIX
model
iron/albedo-qwen3-4b-master3
uid
151
Artifacts
- generated-samples.jsonljsonldownload ↓
- judge-results.jsonljsonldownload ↓
- progress.jsonljsonldownload ↓
- remote-logs.txttxtdownload ↓
- scoring-results.jsonljsonldownload ↓
- duel-transcript.jsonljsonldownload ↓
- verdict.jsonjsondownload ↓