FinToolBench: leaderboard
Financial tool-use benchmark with real tools and APIs, measuring tool invocation, execution success, compliance, and soft-scored task quality.
Metric: Soft Score (score). Source: github.com. Source: benchmarklist.com. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen3-8B | 0.42 | |
| 2 | Doubao-Seed-1.6 | 0.4 | |
| 3 | GLM-4.7-Flash | 0.28 | |
| 4 | GPT-4o | 0.23 | #343 |
Interactive version: theaggregate.ai/benchmark?slug=fintoolbench · How It Works · Data refreshed daily, snapshot 2026-10-20.