mirror of
https://github.com/priyanshujain/messageboardbench.git
synced 2026-10-02 11:07:07 +00:00
archive old experiments and publish swe series
This commit is contained in:
1 parent
480100587e
commit
638e978227
1522 files changed
+220002
-4900
No files matched your search
@@ -0,0 +1,19 @@
|
||||
<svg xmlns="http://www.w3.org/2000/svg" width="1120" height="256" viewBox="0 0 1120 256">
|
||||
<rect width="100%" height="100%" fill="white"/>
|
||||
<text x="20" y="30" font-family="sans-serif" font-size="19" font-weight="bold">Persistence after contradiction recognition</text>
|
||||
<text x="12" y="82" font-family="sans-serif" font-size="12">continued cheating behavior</text>
|
||||
<rect x="285" y="58" width="162.4" height="11" fill="#31688e"/>
|
||||
<text x="453.4" y="68" font-family="sans-serif" font-size="10">GLM 4/17</text>
|
||||
<rect x="285" y="73" width="460.0" height="11" fill="#b05a2a"/>
|
||||
<text x="751.0" y="83" font-family="sans-serif" font-size="10">Muse 10/15</text>
|
||||
<rect x="285" y="88" width="138.0" height="11" fill="#438a5e"/>
|
||||
<text x="429.0" y="98" font-family="sans-serif" font-size="10">DeepSeek 2/10</text>
|
||||
<text x="12" y="148" font-family="sans-serif" font-size="12">safe exit</text>
|
||||
<rect x="285" y="124" width="527.6" height="11" fill="#31688e"/>
|
||||
<text x="818.6" y="134" font-family="sans-serif" font-size="10">GLM 13/17</text>
|
||||
<rect x="285" y="139" width="230.0" height="11" fill="#b05a2a"/>
|
||||
<text x="521.0" y="149" font-family="sans-serif" font-size="10">Muse 5/15</text>
|
||||
<rect x="285" y="154" width="552.0" height="11" fill="#438a5e"/>
|
||||
<text x="843.0" y="164" font-family="sans-serif" font-size="10">DeepSeek 8/10</text>
|
||||
<text x="12" y="244" font-family="sans-serif" font-size="10" fill="#555">GLM and Muse decision-share annotation remains unknown; no value is imputed.</text>
|
||||
</svg>
|
||||
|
After Width: | Height: | Size: 1.4 KiB |
Reference in new issue
Block a user