Leaderboard, made by Qwen DianJin Team (Alibaba Cloud)
FinMCP-Bench
Measures how well LLM agents call real financial MCP tools in single-tool, multi-tool and multi-turn tasks.
FinMCP-Bench v1 (arXiv, 2026-03-26)
TF1 (%), All, higher is better. 6 models.
Updated 26 Mar 2026
FinMCP-Bench v1 (arXiv, 2026-03-26)
TF1 (%), All, higher is better. 6 models.
Updated 26 Mar 2026
- 1Qwen3-235B-A22B-Thinking64.3
- 2Qwen3-30B-A3B-Thinking55.6
- 3Qwen3-4B-Thinking50.1
- 4DeepSeek-R149.9
- 5Seed-OSS-36B39.3
- 6GPT-OSS-20B32.6
| 1 | Qwen3-235B-A22B-Thinking | Qwen | 64.3 | All samples (single-tool, multi-tool, multi-turn), gold conversation history | Paper Table 2 Reported by the authors, reported 26 Mar 2026 · checked 6 Nov 2026 |
|---|---|---|---|---|---|
| 2 | Qwen3-30B-A3B-Thinking | Qwen | 55.6 | All samples (single-tool, multi-tool, multi-turn), gold conversation history | Paper Table 2 Reported by the authors, reported 26 Mar 2026 · checked 6 Nov 2026 |
| 3 | Qwen3-4B-Thinking | Qwen | 50.1 | All samples (single-tool, multi-tool, multi-turn), gold conversation history | Paper Table 2 Reported by the authors, reported 26 Mar 2026 · checked 6 Nov 2026 |
| 4 | DeepSeek-R1 | DeepSeek | 49.9 | All samples (single-tool, multi-tool, multi-turn), gold conversation history | Paper Table 2 Reported by the authors, reported 26 Mar 2026 · checked 6 Nov 2026 |
| 5 | Seed-OSS-36B | Not stated | 39.3 | All samples (single-tool, multi-tool, multi-turn), gold conversation history | Paper Table 2 Reported by the authors, reported 26 Mar 2026 · checked 6 Nov 2026 |
| 6 | GPT-OSS-20B | OpenAI | 32.6 | All samples (single-tool, multi-tool, multi-turn), gold conversation history | Paper Table 2 Reported by the authors, reported 26 Mar 2026 · checked 6 Nov 2026 |