long context benchmark
InfiniteBench/En.MC
InfiniteBench English Multiple Choice variant - first LLM benchmark featuring average data length surpassing 100K tokens for evaluating long-context capabilities with 12 tasks spanning diverse domains
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
InfiniteBench/En.MC leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | ME | 63.3% | 100.0% | 1 | C |
InfiniteBench/En.MC highlights
The top published results on this benchmark's own scale.
What is InfiniteBench/En.MC?
Definition and scoring fields from the benchmark registry.
InfiniteBench English Multiple Choice 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. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- InfiniteBench/En.MC
- Modality
- text
- Primary category
- long context
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- infinitebench-en.mc|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about InfiniteBench/En.MC.
Which model scores highest on InfiniteBench/En.MC?
Llama 3.2 3B Instruct is currently ranked first with 63.3%.
What does InfiniteBench/En.MC measure?
InfiniteBench English Multiple Choice 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 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.