Spaces:
Running
Running
Commit
·
4a49ee3
1
Parent(s):
bfbc587
update paper link
Browse files- leaderboard/md.py +1 -1
leaderboard/md.py
CHANGED
@@ -178,7 +178,7 @@ TOP_TEXT = """# RewardBench: Evaluating Reward Models"""
|
|
178 |
|
179 |
CAPTION_V2 = f"""The *new version* of RewardBench that is based on unseen human data and designed to be substantially more difficult!
|
180 |
|
181 |
-
[Code](https://github.com/allenai/reward-bench) | [Eval. Dataset v2](https://huggingface.co/datasets/allenai/reward-bench-2) | [Results v2](https://huggingface.co/datasets/allenai/reward-bench-2-results) | [Paper](https://
|
182 |
|
183 |
CAPTION_V1 = f"""The original RewardBench -- the first reward model evaluation.
|
184 |
|
|
|
178 |
|
179 |
CAPTION_V2 = f"""The *new version* of RewardBench that is based on unseen human data and designed to be substantially more difficult!
|
180 |
|
181 |
+
[Code](https://github.com/allenai/reward-bench) | [Eval. Dataset v2](https://huggingface.co/datasets/allenai/reward-bench-2) | [Results v2](https://huggingface.co/datasets/allenai/reward-bench-2-results) | [Paper](https://arxiv.org/abs/2506.01937) | Total models: {{}} | Last restart (PST): {current_time}"""
|
182 |
|
183 |
CAPTION_V1 = f"""The original RewardBench -- the first reward model evaluation.
|
184 |
|