FinMTM - Financial Agent: leaderboard
Metric: FinMTM financial agent score (0-100) over 1,000 tool-use tasks with MCP financial tools: tool-call quality (recall-weighted F2 of predicted against reference calls, up to 25) plus judged reasoning (up to 25) and answer correctness against the ground truth (up to 50); higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 22 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash | 62.6 | #93 |
| 2 | Gemini 3 Pro | 54.3 | #77 |
| 3 | GPT-5 | 49.7 | #91 |
| 4 | Qwen 3 VL 235B A22B (Thinking) | 41.5 | #228 (Qwen 3 VL 235B A22B) |
| 5 | Grok 4 Fast (Non-reasoning) | 39.7 | #242 (Grok 4 Fast) |
| 6 | Qwen 3 VL 235B A22B Instruct | 38.7 | #264 |
| 7 | O3 | 35.2 | #121 |
| 8 | GPT-4o | 34.8 | #333 |
| 9 | GLM-4.5V | 32.4 | #339 |
| 10 | Qwen 3 VL 32B (Thinking) | 28.6 | #287 (Qwen 3 VL 32B) |
| 11 | Qwen 3 VL 32B Instruct | 25.1 | #276 |
| 12 | Qwen 3 VL 30B A3B (Thinking) | 23.3 | #338 (Qwen 3 VL 30B A3B) |
| 13 | InternVL3-78B | 22.8 | #345 |
| 14 | Qwen 3 VL 30B A3B Instruct | 20.8 | #365 |
| 15 | Qwen 3 VL 4B Instruct | 19.1 | #506 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=finmtm-financial-agent · How It Works · Data refreshed daily, snapshot 2026-10-11.