felix
commited on
Commit
•
0e46dc8
1
Parent(s):
24806ea
add more links
Browse files
app.py
CHANGED
@@ -66,11 +66,13 @@ for i, img in enumerate(remaining_imgs):
|
|
66 |
|
67 |
st.write(
|
68 |
"""
|
69 |
-
|
70 |
-
|
71 |
-
</li>
|
72 |
-
<li><a href="https://
|
73 |
-
|
|
|
|
|
74 |
</ul>
|
75 |
""", unsafe_allow_html=True
|
76 |
)
|
|
|
66 |
|
67 |
st.write(
|
68 |
"""
|
69 |
+
<p>Leaderboards tracked:</p>
|
70 |
+
<ul>
|
71 |
+
<li><a href="https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard">MT-Bench</a> GPT4 judged evaluation of models</li>
|
72 |
+
<li><a href="https://tatsu-lab.github.io/alpaca_eval/">AlpacaEval</a> GPT4 judged evaluation of models</li>
|
73 |
+
<li><a href="https://www.mosaicml.com/llm-evaluation">MosaicML</a> Balanced set of static benchmarks</li>
|
74 |
+
<li><a href="https://opencompass.org.cn/leaderboard-llm">OpenCompass</a> Balanced set of static benchmarks</li>
|
75 |
+
<li><a href="https://llmbench.ai/data">AgentBench</a> Benchmark evaluating Agent abilities</li>
|
76 |
</ul>
|
77 |
""", unsafe_allow_html=True
|
78 |
)
|