InfiniteBench/En.QA
text
+
+
+
+
About
InfiniteBench En.QA is a long-context question-answering benchmark featuring English questions that evaluate AI models' ability to understand and reason over super-long contexts beyond 100,000 tokens. This benchmark tests models' capacity for extended comprehension, long-range information retrieval, and reasoning abilities when processing extremely lengthy textual inputs.
+
+
+
+
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
19.8%
Average Score
19.8%
High Performers (80%+)
0Top Organizations
#1Meta
1 model
19.8%
+
+
+
+
Leaderboard
1 models ranked by performance on InfiniteBench/En.QA
| License | Links | ||||
|---|---|---|---|---|---|
| Sep 25, 2024 | Llama 3.2 Community License | 19.8% |
