Benchmark
DRACO Benchmark
What is DRACO?
Deep-research style long-context agent tasks; the retrieval and tool stack is part of the score. Benchmark Radar tracks 1 reported scores for DRACO, cited by 1…
- Evaluates
- long context
- Openness
- unknown
- Importer
- Model reports
- Reported scores
- 1
Source provenance
- Original evidence https://huggingface.co/datasets/perplexity-ai/draco
DRACO links
DRACO results and reported scores
Model reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Hy4 preview | Tencent | 77.2 | 2026-08-28 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.
Which sources cite DRACO?
- Hy4 preview Tencent, 2026-08-28