New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
LongBench v1 benchmark
AI model leaderboard for the LongBench v1 benchmark. Compare how large language models score on LongBench v1, see the full ranking, and understand what this AI benchmark measures. Long-context benchmark of 21 tasks at contexts up to 100K tokens.
Leaderboard
No model scores reported yet.
Frequently asked questions about LongBench v1
What is the LongBench v1 benchmark?
Long-context benchmark of 21 tasks at contexts up to 100K tokens.
How is the LongBench v1 benchmark scored?
LongBench v1 is scored using the accuracy (%) metric, where a higher score is better. The maximum achievable score is 100.000. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.
Which AI model scores highest on LongBench v1?
No model scores have been reported for LongBench v1 yet. Check back as the leaderboard is updated.
Is a higher LongBench v1 score better?
Yes. On LongBench v1 a higher score indicates better performance, so models near the top of the leaderboard are the strongest.