Share your thoughts, 1 month free Claude Pro on usSee more

Instruction Following on WildBench

63.18WB Score

CoDIT-Qwen3-8B

Updated 3d ago

Evaluation Results

Method	Links
CoDIT-Qwen3-8B 2026.04		63.18
CoDIT-Gemma3 2026.04		62.21
CoDIT-Qwen3-30B 2026.04		60.23
WebR-Pro 2026.04		54.4
CoDIT-Gemma3 2026.04		54.12
CoDIT-Qwen3-8B 2026.04		48.34
CoDIT-Qwen3-30B 2026.04		48.28
Gemma-2-LMSYS-Chat-1M-Synth 2026.04		46.84
Magpie-Pro-300K-Filtered 2026.04		42.91
Llama-3.1-LMSYS-Chat-1M-Synth 2026.04		42.05
WebR-Basic 2026.04		41.2
WebR-Pro 2026.04		37.19
Gemma-2-LMSYS-Chat-1M-Synth 2026.04		36.2
Llama-3.1-LMSYS-Chat-1M-Synth 2026.04		30.94
WildChat 2026.04		29.99
Magpie-Pro-300K-Filtered 2026.04		26.85
WebR-Basic 2026.04		26.57
WildChat 2026.04		21.69