Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Simulation on CruxEval-I
Loading...
61.4
Pass@1
TAC
13.248
25.749
38.25
50.751
Jun 23, 2026
Pass@1
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@1
TAC
Backbone=Qwen3-4B-Base...
2026.06
61.4
Random
Backbone=Qwen3-4B-Base...
2026.06
59.6
SEC
Backbone=Qwen3-4B-Base...
2026.06
59.5
SEC
Backbone=Qwen3-1.7B
2026.06
42.9
M2O
Backbone=Qwen3-1.7B
2026.06
42.3
TAC
Backbone=Qwen3-1.7B
2026.06
42.2
TAC
Backbone=Llama3.2-3B
2026.06
40.6
Random
Backbone=Llama3.2-3B
2026.06
39.7
Random
Backbone=Qwen3-1.7B
2026.06
37.8
M2O
Backbone=Llama3.2-3B
2026.06
36.1
SEC
Backbone=Llama3.2-3B
2026.06
35.8
SEC
Backbone=Qwen3-0.6B-Ba...
2026.06
33.4
Base
Backbone=Llama3.2-3B
2026.06
31.4
TAC
Backbone=Qwen3-0.6B-Ba...
2026.06
29.6
Random
Backbone=Qwen3-0.6B-Ba...
2026.06
26.9
Base
Backbone=Qwen3-1.7B
2026.06
15.1
Feedback
Search any
task
Search any
task