Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Short-chain composition on E2 jointly stable facts
Loading...
181
Example Stable Count
Qwen3-8B
152.92
160.21
167.5
174.79
May 26, 2026
Example Stable Count
Consistent Stable Count
Gate Count
Consistent Failure Count
Updated 7d ago
Evaluation Results
Method
Method
Links
Example Stable Count
Consistent Stable Count
Gate Count
Consistent Failure Count
Qwen3-8B
Atoms=1 400
2026.05
181
220
360
0
DeepHermes-3-Llama-3-8B
Atoms=1 400
2026.05
168
216
360
59
Qwen2.5-7B
Atoms=1 400
2026.05
162
194
360
39
Mistral-7B
Atoms=1 400
2026.05
154
202
360
60
Feedback
Search any
task
Search any
task