Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
RO reformulation on Random
Loading...
96.9
Accuracy
AutoREM
44.9
58.4
71.9
85.4
May 12, 2026
Accuracy
Output Tokens
Updated 21d ago
Evaluation Results
Method
Method
Links
Accuracy
Output Tokens
AutoREM
Base LLM=DeepSeek-V3.2...
2026.05
96.9
2,006
ACE
Base LLM=DeepSeek-V3.2...
2026.05
71.9
3,184
Expert Prompt
Base LLM=DeepSeek-V3.2...
2026.05
68.8
3,734
Max Thinking
Base LLM=DeepSeek-V3.2...
2026.05
59.4
13,971
ReasoningBank
Base LLM=DeepSeek-V3.2...
2026.05
53.1
2,510
Base LLM
Base LLM=DeepSeek-V3.2...
2026.05
46.9
4,748
Feedback
Search any
task
Search any
task