Updated daily at 05:00 UTC
Benchmark
LongBench v2
Measures: 503 multiple-choice questions over contexts of 8K to 2M words in six task types (single- and multi-document QA, long in-context learning, long dialogue history, code repositories, long structured data); scored by accuracy.
- Maintainer
- THUDM, Tsinghua University (Yushi Bai et al.)
- Introduced
- 2024
- Status
- Active
- Saturation
- Headroom
- Typical provenance
- Self-reported
- In scoring set
- No
Leaderboard
Independent and third-party results only.
No independent or third-party results yet. Show all results