Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Spatial Reasoning on ShuffleObj
Loading...
44.1
NL-to-Format Accuracy
Qwen3-1.7B
16.852
23.926
31
38.074
Jan 12, 2026
NL-to-Format Accuracy
In-Writing Accuracy (Base)
In-Writing Accuracy (IF)
In-Writing Accuracy (BF)
Updated 4d ago
Evaluation Results
Method
Method
Links
NL-to-Format Accuracy
In-Writing Accuracy (Base)
In-Writing Accuracy (IF)
In-Writing Accuracy (BF)
Qwen3-1.7B
Shot=0
2026.01
44.1
43.4
45.4
45.4
Qwen3-1.7B
Shot=4
2026.01
35.6
35.3
46.2
46.3
Qwen3-1.7B
Shot=1
2026.01
34
33.7
48.1
46.2
SmolLM2-1.7B
Shot=0
2026.01
18.2
18.2
18
18
SmolLM2-1.7B
Shot=4
2026.01
18.1
16.4
19.7
19.2
SmolLM2-1.7B
Shot=1
2026.01
17.9
17.6
18.4
18.8
Feedback
Search any
task
Search any
task