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

Tool Using on Non-Live P-Mul

87.5Accuracy

ISO-C

Updated 1mo ago

Evaluation Results

Method	Links
ISO-C 2026.06		87.5
ISO-CTS 2026.06		87.5
DARE + TIES 2026.06		87
TA 2026.06		86.5
TSV-Merge 2026.06		86.5
RESMERGE 2026.06		86.5
TIES 2026.06		86
RAM 2026.06		86
MemoryAgent 2026.06		85
ToolRL 2026.06		85
AMPO 2026.06		84
Qwen2.5-7B-Instruct 2026.06		82.5
General-Reasoner 2026.06		81.5
TA 2026.06		75.5
RESMERGE 2026.06		72.5
GRPO 2026.06		72
Spiral 2026.06		71.5
TSV-Merge 2026.06		71.5
RAM 2026.06		61.5
TIES 2026.06		55.5
Qwen3-4B 2026.06		28
DARE + TIES 2026.06		27.5