MRCR v2
text
+
+
+
+
About
MRCR-v2 represents the second iteration of the Multi-hop Reasoning for Conversational Recommendation benchmark, incorporating enhanced evaluation protocols and expanded conversation scenarios. This updated version addresses limitations in the original benchmark while providing improved assessment of models' multi-step reasoning capabilities in recommendation dialogues.
+
+
+
+
Evaluation Stats
Total Models1
Organizations1
Verified Results0
Self-Reported1
+
+
+
+
Benchmark Details
Max Score1
Language
en
+
+
+
+
Performance Overview
Score distribution and top performers
Score Distribution
1 models
Top Score
16.6%
Average Score
16.6%
High Performers (80%+)
0Top Organizations
#1Google
1 model
16.6%
+
+
+
+
Leaderboard
1 models ranked by performance on MRCR v2
| License | Links | ||||
|---|---|---|---|---|---|
| Jun 17, 2025 | Creative Commons Attribution 4.0 License | 16.6% |
