FinToolBench - Tool Execution Success Rate: leaderboard
Metric: Tool Execution Success Rate (TESR, 0-1, times 100): share of all questions whose final tool call returns a valid parsed output without error (intermediate failures and retries allowed), on the 295 tool-required financial questions (166 single-tool, 129 multi-tool) over 760 free-tier RapidAPI and AkShare tools, with the model as the planner of the authors' FATR agent (BGE-M3 retrieval of candidate tools, finance-attribute tool cards, ReAct loop of at most 5 tool steps); higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Seed-1.6 | 32.54 | #257 |
| 2 | Qwen 3 8B | 29.49 | #667 |
| 3 | Claude Sonnet 4.5 | 24.07 | #138 |
| 4 | GLM-4.7 Flash | 21.02 | #496 |
| 5 | Grok 3 | 19.32 | #296 |
| 6 | GPT-5.4 | 13.22 | #76 |
| 7 | Gemini 3.1 Pro (Preview) | 11.86 | #54 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=fintoolbench-tool-execution-success-rate · How It Works · Data refreshed daily, snapshot 2026-10-11.