LiveBench 20241125
text
+
+
+
+
About
LiveBench 20241125 is a specific snapshot of the LiveBench evaluation suite from November 25, 2024, featuring questions and tasks current to that date. This version provides contamination-free assessment of AI models using contemporary problems that couldn't have been in training data, measuring genuine reasoning and knowledge capabilities with time-stamped evaluation consistency.
+
+
+
+
Evaluation Stats
Total Models4
Organizations1
Verified Results0
Self-Reported4
+
+
+
+
Benchmark Details
Max Score1
Language
en
+
+
+
+
Performance Overview
Score distribution and top performers
Score Distribution
4 models
Top Score
78.4%
Average Score
76.5%
High Performers (80%+)
0Top Organizations
#1Alibaba Cloud / Qwen Team
4 models
76.5%
+
+
+
+
Leaderboard
4 models ranked by performance on LiveBench 20241125
| License | Links | ||||
|---|---|---|---|---|---|
| Jul 25, 2025 | Apache 2.0 | 78.4% | |||
| Sep 10, 2025 | Apache 2.0 | 76.6% | |||
| Sep 10, 2025 | Apache 2.0 | 75.8% | |||
| Jul 22, 2025 | Apache 2.0 | 75.4% |
