Update leaderboard.md

Author: mtian8

docs/leaderboard.md

@@ -4,22 +4,25 @@
 
 # SciCode Leaderboard
 
-| Model                  | Main Problem Resolve Rate |
-|------------------------|---------------------------|
-| 🥇OpenAI o1-preview     | 7.7%                      |
-| 🥈Claude3.5-Sonnet      | 4.6%                      |
-| 🥉Deepseek-Coder-v2     | 3.1%                      |
-| GPT-4o                 | 1.5%                      |
-| GPT-4-Turbo            | 1.5%                      |
-| OpenAI o1-mini         | 1.5%                      |
-| Gemini 1.5 Pro         | 1.5%                      |
-| Claude3-Opus           | 1.5%                      |
-| Claude3-Sonnet         | 1.5%                      |
-| Qwen2-72B-Instruct     | 1.5%                      |
-| Llama-3.1-405B-Instruct| 0%                        |
-| Llama-3.1-70B-Instruct | 0%                        |
-| Mixtral-8x22B-Instruct | 0%                        |
-| Llama-3-70B-Chat       | 0%                        |
+| Models                   | Main Problem Resolve Rate           | <span style="background-color:lightgrey">Subproblem</span>            |
+|--------------------------|-------------------------------------|-------------------------------------|
+| 🥇 OpenAI o1-preview      | <div align="center">7.7</div>       | <div align="center" style="background-color:lightgrey">28.5</div>     |
+| 🥈 Claude3.5-Sonnet       | <div align="center">4.6</div>       | <div align="center" style="background-color:lightgrey">26.0</div>     |
+| 🥉 Claude3.5-Sonnet (new) | <div align="center">4.6</div>       | <div align="center" style="background-color:lightgrey">25.3</div>     |
+| Deepseek-Coder-v2        | <div align="center">3.1</div>       | <div align="center" style="background-color:lightgrey">21.2</div>     |
+| GPT-4o                   | <div align="center">1.5</div>       | <div align="center" style="background-color:lightgrey">25.0</div>     |
+| GPT-4-Turbo              | <div align="center">1.5</div>       | <div align="center" style="background-color:lightgrey">22.9</div>     |
+| OpenAI o1-mini           | <div align="center">1.5</div>       | <div align="center" style="background-color:lightgrey">22.2</div>     |
+| Gemini 1.5 Pro           | <div align="center">1.5</div>       | <div align="center" style="background-color:lightgrey">21.9</div>     |
+| Claude3-Opus             | <div align="center">1.5</div>       | <div align="center" style="background-color:lightgrey">21.5</div>     |
+| Llama-3.1-405B-Chat      | <div align="center">1.5</div>       | <div align="center" style="background-color:lightgrey">19.8</div>     |
+| Claude3-Sonnet           | <div align="center">1.5</div>       | <div align="center" style="background-color:lightgrey">17.0</div>     |
+| Qwen2-72B-Instruct       | <div align="center">1.5</div>       | <div align="center" style="background-color:lightgrey">17.0</div>     |
+| Llama-3.1-70B-Chat       | <div align="center">0.0</div>       | <div align="center" style="background-color:lightgrey">17.0</div>     |
+| Mixtral-8x22B-Instruct   | <div align="center">0.0</div>       | <div align="center" style="background-color:lightgrey">16.3</div>     |
+| Llama-3-70B-Chat         | <div align="center">0.0</div>       | <div align="center" style="background-color:lightgrey">14.6</div>     |
+
+Note: If the models tie in the Main Problem resolve rate, we will then compare the Subproblems.
 
 <!-- Once you've added the results to the submission repository,
      bring back the table here -->