Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (Source Lib., Unseen Lib., Delta)
Loading...
93.21
Accuracy (Source Lib.)
CARD
87.0844
88.6747
90.265
91.8553
Jun 18, 2026
Accuracy (Source Lib.)
Accuracy (Unseen Lib.)
Performance Delta (Source - Unseen)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy (Source Lib.)
Accuracy (Unseen Lib.)
Performance Delta (Source - Unseen)
CARD
Base Model=GPT-4o-mini
2026.06
93.21
91.44
1.77
SIGMA
Base Model=GPT-4o-mini
2026.06
92.96
91.86
1.1
G-Designer
Base Model=GPT-4o-mini
2026.06
89.26
87.28
1.98
GPTSwarm
Base Model=GPT-4o-mini
2026.06
87.83
84.47
3.36
LLM-Debate
Base Model=GPT-4o-mini
2026.06
87.32
85.29
2.03
Feedback
Search any
task
Search any
task