Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Chinese Idiom Cloze Completion on CHID (held-out)
Loading...
70.3
DBS
SOURCEbest
1.244
19.172
37.1
55.028
Feb 11, 2026
DBS
DVSavg@32
Updated 4d ago
Evaluation Results
Method
Method
Links
DBS
DVSavg@32
SOURCEbest
2026.02
70.3
-
EXPERT
Model=Qwen3-1.7B optim...
2026.02
59.8
-
SOURCEavg
2026.02
49.3
-
DataChef-32B
Oracle Upper Bound=tru...
2026.02
45.7
-
Gemini-3-Pro
2026.02
21.9
29.7
DataChef-32B
2026.02
20.5
7.9
Qwen3-32B
2026.02
12.3
1.1
Qwen3-Next ⊕ Kimi-K2
Reasoning backbone=Qwe...
2026.02
4.1
8.6
Kimi-K2
2026.02
3.9
23.1
Feedback
Search any
task
Search any
task