Instruction Following Evaluation on PPE-IFEval

76Score

Rubric-ARROW-voting@5

Updated 5d ago

Evaluation Results

Method	Links
Rubric-ARROW-voting@5 2026.05		76
RIFL-voting@5 2026.05		75.8
Gemini-2.5-Flash 2026.05		75
RIFL 2026.05		73.3
Rubric-ARROW 2026.05		72.6
Rubric-ARROW w/o RL-voting@5 2026.05		72.2
Rubric-RM-voting@5 2026.05		70.8
Rubric-ARROW w/o RL 2026.05		69.5
Rubric-RM 2026.05		67
RM-R1-32B (DeepSeek-Dist) 2026.05		63.2
RM-R1-14B (DeepSeek-Dist) 2026.05		61.2
API Prompting (Rubric+Judge pairwise) 2026.05		61
RM-R1-32B (Qwen-2.5-Inst) 2026.05		60.4
RRM-32B 2026.05		60.2
API Prompting (direct Judge) 2026.05		59.2
RM-R1-14B (Qwen-2.5-Inst) 2026.05		59
Claude-3.5-Sonnet 2026.05		58
RM-R1-7B (Qwen-2.5-Inst) 2026.05		55.2
Qwen-3-8B (Rubric+Judge pairwise) 2026.05		53.8
Qwen-3-8B (Rubric+Judge pointwise) 2026.05		52.6
RM-R1-7B (DeepSeek-Dist) 2026.05		51
RRM-7B 2026.05		51
JudgeLRM-7B 2026.05		46
API Prompting (Rubric+Judge pointwise) 2026.05		26.4