Timeline of Undisclosed

Undisclosed scores 29.59% on SWE-bench Multimodal

Undisclosed scores 20.33% on SWE-bench Lite

Undisclosed scores 26.67% on SWE-bench Lite

Undisclosed scores 29.67% on SWE-bench Lite

Undisclosed scores 30% on SWE-bench Lite

Undisclosed scores 31.33% on SWE-bench Lite

Undisclosed scores 33% on SWE-bench Lite

Undisclosed scores 34% on SWE-bench Lite

Undisclosed scores 35% on SWE-bench Lite

Undisclosed scores 35.67% on SWE-bench Lite

Undisclosed scores 35.67% on SWE-bench Lite

Undisclosed scores 38.33% on SWE-bench Lite

Undisclosed scores 39.33% on SWE-bench Lite

Undisclosed scores 44% on SWE-bench Lite

Undisclosed scores 48.33% on SWE-bench Lite

Undisclosed scores 48.67% on SWE-bench Lite

Undisclosed scores 49% on SWE-bench Lite

Undisclosed scores 55% on SWE-bench Lite

Undisclosed scores 25.6% on SWE-bench Verified

Undisclosed scores 25.8% on SWE-bench Verified

Undisclosed scores 31.6% on SWE-bench Verified

Undisclosed scores 32% on SWE-bench Verified

Undisclosed scores 37% on SWE-bench Verified

Undisclosed scores 38.8% on SWE-bench Verified

Undisclosed scores 40.6% on SWE-bench Verified

Undisclosed scores 41.6% on SWE-bench Verified

Undisclosed scores 43.6% on SWE-bench Verified

Undisclosed scores 45.2% on SWE-bench Verified

Undisclosed scores 45.4% on SWE-bench Verified

Undisclosed scores 50% on SWE-bench Verified

Undisclosed scores 50% on SWE-bench Verified

Undisclosed scores 53.2% on SWE-bench Verified

Undisclosed scores 55% on SWE-bench Verified

Undisclosed scores 56.6% on SWE-bench Verified

Undisclosed scores 57% on SWE-bench Verified

Undisclosed scores 58.2% on SWE-bench Verified

Undisclosed scores 62.8% on SWE-bench Verified

Undisclosed scores 65.4% on SWE-bench Verified

Undisclosed scores 65.4% on SWE-bench Verified

Undisclosed scores 65.8% on SWE-bench Verified

Undisclosed scores 70.4% on SWE-bench Verified

Undisclosed scores 70.6% on SWE-bench Verified

Undisclosed scores 13.82% on SWE-bench (full test split)

Undisclosed scores 19.27% on SWE-bench (full test split)

Undisclosed scores 19.75% on SWE-bench (full test split)

Undisclosed scores 22.06% on SWE-bench (full test split)

Undisclosed scores 29.99% on SWE-bench (full test split)

Undisclosed scores 37.1% on SWE-bench (full test split)

Undisclosed scores 41.98% on SWE-bench (full test split)