BankerToolBench
We show this table for reference; we do not rank on it.
A display-only provider benchmark for finance-oriented tool-use and agent workflows.
Benchmark score on BankerToolBench — November 13, 2026
We compile the BankerToolBench rows from provider self-reports. Hy4 preview leads the table at 78.6%, followed by MiniMax M3.1 Flash (76.2%) and MiniMax M3 (76.1%). We do not use these results to rank models overall.
Hy4 preview
Tencent
Reported by TencentMiniMax M3.1 Flash
MiniMax
Reported by MiniMaxMiniMax M3
MiniMax
Reported by MiniMax3 modelsAgenticCurrentDisplay onlyUpdated November 13, 2026
Benchmark score table (3 models)
All 3 results on this page were reported by the labs that built the models.
| Rank | Model / configuration | Score | Who ran it | Parameters (B) | Open / closed |
|---|---|---|---|---|---|
| 1 | Hy4 previewTencentReported by Tencent | 78.6% | Reported by Tencent | Not reported | Open |
| 2 | MiniMax M3.1 FlashMiniMaxReported by MiniMax | 76.2% | Reported by MiniMax | Not reported | Closed |
| 3 | MiniMax M3MiniMaxReported by MiniMax | 76.1% | Reported by MiniMax | Not reported | Open |
- Lab-reported
- Benchmark-run
- Independent
Among the reported BankerToolBench rows, Hy4 preview is first at 78.6%. The third row is 2.5 points behind. The broader top-10 range is 2.5 points, so many of the published results sit in a relatively narrow band.
3 models have been evaluated on BankerToolBench. The benchmark falls in the Agentic category. BankerToolBench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About BankerToolBench
Year
2026
Tasks
Finance and banking tool-use tasks
Format
Task success rate
Difficulty
Professional finance-agent workflows
MiniMax reports BankerToolBench in the M3 comparison chart. BenchLM tracks it as display-only because it is not part of the weighted agentic schema.
Freshness and provenance
Version
BankerToolBench 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does BankerToolBench measure?
A display-only provider benchmark for finance-oriented tool-use and agent workflows.
Which model scores highest on BankerToolBench?
Hy4 preview by Tencent currently leads with a score of 78.6% on BankerToolBench.
How many models are evaluated on BankerToolBench?
3 AI models have published results on BankerToolBench in the BenchLM catalog.
Compare top models on BankerToolBench
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.