Benchmark
BankerToolBench
What is BankerToolBench?
End-to-end investment-banking tasks produce spreadsheets, presentations, and documents; the agent harness, financial-data tools, and rubric-grader…
- Evaluates
- professional
- Openness
- unknown
- Importer
- Model reports
- Reported scores
- 1
Source provenance
- Original evidence https://github.com/Handshake-AI-Research/bankertoolbench
BankerToolBench code
BankerToolBench results and reported scores
Model reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Hy4 preview | Tencent | 78.6 | 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 BankerToolBench?
- Hy4 preview Tencent, 2026-08-28