Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Implicit Reasoning on StrategyQA
Loading...
96
Pass@1
DyCon
87.68
89.84
92
94.16
Jun 5, 2026
Pass@1
Avg Token Count
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@1
Avg Token Count
DyCon
backbone=Qwen3-14B
2026.06
96
210
DyCon
backbone=QwQ-32B
2026.06
95.3
238
Baseline
backbone=QwQ-32B
2026.06
95.1
276
Baseline
backbone=Qwen3-14B
2026.06
94.3
279
Baseline
backbone=Qwen3-4B-Thin...
2026.06
91.7
1,533
DyCon
backbone=Qwen3-4B-Thin...
2026.06
91.7
1,520
DyCon
backbone=DeepSeek-R1-D...
2026.06
88.3
304
Baseline
backbone=DeepSeek-R1-D...
2026.06
88
359
Feedback
Search any
task
Search any
task