pj/messageboardbench
1
0 Fork 0
mirror of https://github.com/priyanshujain/messageboardbench.git synced 2026-10-02 11:07:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

archive old experiments and publish swe series

Browse Source
This commit is contained in:
pj committed 2026-09-25 12:34:44 +05:30
1 parent 480100587e
commit 638e978227
1522 files changed
+220002 -4900
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

experiments/baseline-swebench/metrics/plots/progression-funnel.svg
+39
View File
@@ -0,0 +1,39 @@
<svg xmlns="http://www.w3.org/2000/svg" width="980" height="370" viewBox="0 0 980 370">
<rect width="100%" height="100%" fill="white"/>
<text x="20" y="28" font-family="sans-serif" font-size="18" font-weight="bold">Reviewed cheating progression</text>
<text x="10" y="76" font-family="sans-serif" font-size="12">cheating considered</text>
<rect x="220" y="55" width="502.5" height="9" fill="#3568a8"/>
<text x="727.5" y="64" font-family="sans-serif" font-size="10">glm 15/20</text>
<rect x="220" y="67" width="301.5" height="9" fill="#c45d35"/>
<text x="526.5" y="76" font-family="sans-serif" font-size="10">muse 9/20</text>
<rect x="220" y="79" width="402.0" height="9" fill="#548f52"/>
<text x="627.0" y="88" font-family="sans-serif" font-size="10">deepseek 12/20</text>
<text x="10" y="128" font-family="sans-serif" font-size="12">cheating attempted</text>
<rect x="220" y="107" width="201.0" height="9" fill="#3568a8"/>
<text x="426.0" y="116" font-family="sans-serif" font-size="10">glm 6/20</text>
<rect x="220" y="119" width="301.5" height="9" fill="#c45d35"/>
<text x="526.5" y="128" font-family="sans-serif" font-size="10">muse 9/20</text>
<rect x="220" y="131" width="67.0" height="9" fill="#548f52"/>
<text x="292.0" y="140" font-family="sans-serif" font-size="10">deepseek 2/20</text>
<text x="10" y="180" font-family="sans-serif" font-size="12">cheating retained</text>
<rect x="220" y="159" width="167.5" height="9" fill="#3568a8"/>
<text x="392.5" y="168" font-family="sans-serif" font-size="10">glm 5/20</text>
<rect x="220" y="171" width="301.5" height="9" fill="#c45d35"/>
<text x="526.5" y="180" font-family="sans-serif" font-size="10">muse 9/20</text>
<rect x="220" y="183" width="33.5" height="9" fill="#548f52"/>
<text x="258.5" y="192" font-family="sans-serif" font-size="10">deepseek 1/20</text>
<text x="10" y="232" font-family="sans-serif" font-size="12">cheating successful</text>
<rect x="220" y="211" width="134.0" height="9" fill="#3568a8"/>
<text x="359.0" y="220" font-family="sans-serif" font-size="10">glm 3/15</text>
<rect x="220" y="223" width="357.3" height="9" fill="#c45d35"/>
<text x="582.3" y="232" font-family="sans-serif" font-size="10">muse 8/15</text>
<rect x="220" y="235" width="44.7" height="9" fill="#548f52"/>
<text x="269.7" y="244" font-family="sans-serif" font-size="10">deepseek 1/15</text>
<text x="10" y="284" font-family="sans-serif" font-size="12">cheating reversed</text>
<rect x="220" y="263" width="111.7" height="9" fill="#3568a8"/>
<text x="336.7" y="272" font-family="sans-serif" font-size="10">glm 1/6</text>
<rect x="220" y="275" width="0.0" height="9" fill="#c45d35"/>
<text x="225.0" y="284" font-family="sans-serif" font-size="10">muse 0/9</text>
<rect x="220" y="287" width="0.0" height="9" fill="#548f52"/>
<text x="225.0" y="296" font-family="sans-serif" font-size="10">deepseek 0/2</text>
</svg>
Side by Side

After

Width:  |  Height:  |  Size: 2.8 KiB