Skip to content

Commit ba74df9

Browse files
committed
update leaderboard
1 parent 4a316d6 commit ba74df9

File tree

1 file changed

+7
-4
lines changed

1 file changed

+7
-4
lines changed

docs/leaderboard.md

+7-4
Original file line numberDiff line numberDiff line change
@@ -6,9 +6,12 @@
66

77
| Models | Main Problem Resolve Rate | <span style="color:grey">Subproblem</span> |
88
|--------------------------|-------------------------------------|-------------------------------------|
9-
| 🥇 OpenAI o1-preview | <div align="center">**7.7**</div> | <div align="center" style="color:grey">28.5</div> |
10-
| 🥈 Claude3.5-Sonnet | <div align="center">**4.6**</div> | <div align="center" style="color:grey">26.0</div> |
11-
| 🥉 Claude3.5-Sonnet (new) | <div align="center">**4.6**</div> | <div align="center" style="color:grey">25.3</div> |
9+
| 🥇 OpenAI o3-mini | <div align="center">**9.2**</div> | <div align="center" style="color:grey">33.0</div> |
10+
| 🥈 OpenAI o1-preview | <div align="center">**7.7**</div> | <div align="center" style="color:grey">28.5</div> |
11+
| 🥉 Deepseek-R1 | <div align="center">**4.6**</div> | <div align="center" style="color:grey">28.5</div> |
12+
| Claude3.5-Sonnet | <div align="center">**4.6**</div> | <div align="center" style="color:grey">26.0</div> |
13+
| Claude3.5-Sonnet (new) | <div align="center">**4.6**</div> | <div align="center" style="color:grey">25.3</div> |
14+
| Deepseek-v3 | <div align="center">**3.1**</div> | <div align="center" style="color:grey">23.7</div> |
1215
| Deepseek-Coder-v2 | <div align="center">**3.1**</div> | <div align="center" style="color:grey">21.2</div> |
1316
| GPT-4o | <div align="center">**1.5**</div> | <div align="center" style="color:grey">25.0</div> |
1417
| GPT-4-Turbo | <div align="center">**1.5**</div> | <div align="center" style="color:grey">22.9</div> |
@@ -31,4 +34,4 @@
3134
</center>
3235

3336
!!! tip "How to submit"
34-
Want to submit your own model? Head over to the [documentation](docs/index.md).
37+
Want to submit your own model? Submit a request via a [Github issue](https://github.com/scicode-bench/SciCode/issues).

0 commit comments

Comments
 (0)