back to mission control
ALBEDO-5FJCCXchallenger37.00
ALBEDO-XXXIIking63.00
Δ margin-26.0
margin
-26.10 pp
judges
3 panel
turns
128/128
vllm errors
0c / 0k
finished
Jun 17, 08:49
Judge panel
GLMlose
chal
37.70
king
62.30
QWENlose
chal
37.00
king
63.00
DEEPSEEKlose
chal
32.90
king
67.10
Metrics
progress
32.20
protocol
47.00
grounding
34.10
efficiency
31.90
correctness
34.00
King it faced
era
ALBEDO-XXXII
model
arboshelper/albedo-qwen3-4b-2-5-final
uid
159
Artifacts
- generated-samples.jsonljsonldownload ↓
- judge-results.jsonljsonldownload ↓
- progress.jsonljsonldownload ↓
- remote-logs.txttxtdownload ↓
- scoring-results.jsonljsonldownload ↓
- duel-transcript.jsonljsonldownload ↓
- verdict.jsonjsondownload ↓