nielsr HF Staff commited on
Commit
42e49f5
·
verified ·
1 Parent(s): 74797c9

Add community evaluation results for DeepSWE

Browse files

This PR adds community-provided evaluation results for the following benchmarks:

- **[DeepSWE](https://huggingface.co/datasets/datacurve/deep-swe?eval_result=moonshotai/Kimi-K2.7-Code&leaderboard_task_id=deep_swe)**

These results were extracted from the official [DeepSWE leaderboard](https://deepswe.datacurve.ai/). This is based on the new [evaluation results feature](https://huggingface.co/docs/hub/eval-results).

*Note: This is an automated PR. Please review the evaluation results before merging.*

Files changed (1) hide show
  1. .eval_results/deep-swe.yaml +8 -0
.eval_results/deep-swe.yaml ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: datacurve/deep-swe
3
+ task_id: deep_swe
4
+ value: 30.53
5
+ notes: "Pass@1 over 452 attempts on 113 tasks, mini-swe-agent harness."
6
+ source:
7
+ url: https://deepswe.datacurve.ai/
8
+ name: DeepSWE Leaderboard