long context benchmark
InfiniteBench/En.QA
InfiniteBench English Question Answering variant - first LLM benchmark featuring average data length surpassing 100K tokens for evaluating long-context capabilities with 12 tasks spanning diverse domains
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
InfiniteBench/En.QA Ranking
Higher score ranks better on this benchmark.
| 01 | ME | 19.8% | 100.0% | 1 | C |
InfiniteBench/En.QA Highlights
The leading models and scores on this benchmark.
What is InfiniteBench/En.QA?
What InfiniteBench/En.QA measures and how its scores work.
InfiniteBench English Question Answering variant - first LLM benchmark featuring average data length surpassing 100K tokens for evaluating long-context capabilities with 12 tasks spanning diverse domains
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- InfiniteBench/En.QA
- Modality
- text
- Primary category
- long context
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- infinitebench-en.qa|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about InfiniteBench/En.QA.
Which model scores highest on InfiniteBench/En.QA?
Llama 3.2 3B Instruct is currently ranked first with 19.8%.
What does InfiniteBench/En.QA measure?
InfiniteBench English Question Answering variant - first LLM benchmark featuring average data length surpassing 100K tokens for evaluating long-context capabilities with 12 tasks spanning diverse domains
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.