Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Molecule Editing on ChemCoTBench
Loading...
100
Addition Success Rate
Gemini-2.5-Pro-think
37.6
53.8
70
86.2
Jan 25, 2026
Addition Success Rate
Deletion Success Rate
Substitution Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Addition Success Rate
Deletion Success Rate
Substitution Success Rate
Gemini-2.5-Pro-think
2026.01
100
85
81.7
Claude3.7-sonnet-think
2026.01
85
80
83.4
ChemCRAFT
2026.01
85
95
80
DeepSeek-R1
2026.01
70
70
68.3
Deepseek-V3
2026.01
70
75
76.7
O3-Mini
2026.01
65
55
80
Qwen2.5-32B-Instruct
2026.01
50
50
48.3
Qwen3-235B-A22B
2026.01
40
75
66.7
Feedback
Search any
task
Search any
task