Add eval instructions

index.html

@@ -4383,6 +4383,9 @@ <h3 class="text-title" style="margin-bottom:0.5em">Citation</h3>
               <a href="https://princeton-nlp.github.io/">
                 <img src="img/princeton_seal.svg" style="height: 3em;padding-top:0.5em;padding-right: 1em" />
               </a>
+              <a href="https://www.cs.stanford.edu/">
+                <img src="img/stanford_logo.png" style="height: 3em;padding-top:0.5em;padding-right: 1em;padding-left: 0.25em;" />
+              </a>
               <a href="https://pli.princeton.edu/">
                 <img src="img/pli_logo.svg" style="height: 3em;padding-top:0.5em;padding-right: 1em" />
               </a>

multimodal.html

@@ -105,10 +105,10 @@ <h3 style="font-size: 20px; padding-top: 1.2em">ICLR 2025</h3>
             <h2 class="text-title">About</h2>
             <img src="img/teaser_mm.png" style="width:80%;margin:auto;display:block;"/>
             <p class="text-content">
-                SWE-bench Multimodal is a dataset for evaluating AI systems on visual software engineering tasks.
-                It contains 619 task instances from 17 popular JavaScript repositories, each featuring images crucial to problem-solving.
-                The dataset covers a range of challenges including UI glitches, map rendering problems, or data visualization bugs.
-                SWE-bench Multimodal challenges AI systems to tackle the diverse, multimodal nature of modern software development.
+              SWE-bench Multimodal is a dataset for evaluating AI systems on visual software engineering tasks.
+              It contains 619 task instances from 17 popular JavaScript repositories, each featuring images crucial to problem-solving.
+              The dataset covers a range of challenges including UI glitches, map rendering problems, or data visualization bugs.
+              SWE-bench Multimodal challenges AI systems to tackle the diverse, multimodal nature of modern software development.
             </p class="text-content">
             <h3 class="text-title" style="margin-bottom:0.5em">Citation</h3>
             <pre id="citation" style="border-color: #2F4F4F;"><code>@misc{yang2024swebenchmultimodalaisystems,

submit.html

@@ -95,6 +95,26 @@ <h1 style="font-size: 60px; padding-top: 0.4em">Submit to SWE-bench</h1>
                 </a>
             </div>
         </div>
+        <div class="content-wrapper">
+            <div class="content-box">
+                <h3>
+                    Evaluating on SWE-bench
+                </h3>
+                <p>
+                    Check out the main <a href="https://github.com/swe-bench/SWE-bench">SWE-bench</a> repository
+                    for instructions on how to generate and evaluate predictions on SWE-bench [Lite, Verified, Multimodal].
+                </p>
+                <p style="margin-top: 0.5em">
+                    SWE-bench evaluation can be carried out either locally or via cloud compute platforms with our
+                    <a href="https://github.com/swe-bench/sb-cli/">sb-cli</a> tool (Recommended) or
+                    <a href="https://github.com/swe-bench/SWE-bench/blob/main/assets/evaluation.md">Modal</a>.
+                </p>
+                <p style="margin-top: 0.5em">
+                    Evaluation for the test split of SWE-bench Multimodal is exclusively available via
+                    <a href="https://github.com/swe-bench/sb-cli/">sb-cli</a>.
+                </p>
+            </div>
+        </div>
         <div class="content-wrapper">
             <div class="content-box">
                 <h3>

template/template_index.html

@@ -460,6 +460,9 @@ <h3 class="text-title" style="margin-bottom:0.5em">Citation</h3>
               <a href="https://princeton-nlp.github.io/">
                 <img src="img/princeton_seal.svg" style="height: 3em;padding-top:0.5em;padding-right: 1em" />
               </a>
+              <a href="https://www.cs.stanford.edu/">
+                <img src="img/stanford_logo.png" style="height: 3em;padding-top:0.5em;padding-right: 1em;padding-left: 0.25em;" />
+              </a>
               <a href="https://pli.princeton.edu/">
                 <img src="img/pli_logo.svg" style="height: 3em;padding-top:0.5em;padding-right: 1em" />
               </a>