long context benchmark
CorpusQA 1M
CorpusQA 1M is a long-context question answering benchmark designed to evaluate models at approximately 1 million token contexts. Models are scored on accuracy when retrieving and reasoning over information distributed across an extremely long input corpus.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
CorpusQA 1M Ranking
Higher score ranks better on this benchmark.
| 1 | DE | 62.0% | 100.0% | 2 | C | |
| 2 | DE | 60.5% | 0.0% | 2 | C |
CorpusQA 1M Score Distribution
A closer view of the leading scores on this benchmark.
CorpusQA 1M Highlights
The leading models and scores on this benchmark.
What is CorpusQA 1M?
What CorpusQA 1M measures and how its scores work.
CorpusQA 1M is a long-context question answering benchmark designed to evaluate models at approximately 1 million token contexts. Models are scored on accuracy when retrieving and reasoning over information distributed across an extremely long input corpus.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- CorpusQA 1M
- Modality
- text
- Primary category
- long context
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- corpusqa-1m|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about CorpusQA 1M.
Which model scores highest on CorpusQA 1M?
DeepSeek-V4-Pro-Max is currently ranked first with 62.0%.
What does CorpusQA 1M measure?
CorpusQA 1M is a long-context question answering benchmark designed to evaluate models at approximately 1 million token contexts. Models are scored on accuracy when retrieving and reasoning over information distributed across an extremely long input corpus.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 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.