FinMTM - Single-Choice: leaderboard
Metric: FinMTM single-choice score (%) on the 1,982 single-choice questions (distractors written by Gemini 3 Pro) built from expert-validated financial chart and report questions (Chinese and English), set-overlap scoring with no over-selection: any wrong option scores 0, otherwise credit is the share of correct options chosen; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 22 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro | 92.1 | #77 |
| 2 | Gemini 3 Flash | 91.9 | #93 |
| 3 | GPT-5 | 89 | #91 |
| 4 | O3 | 85.8 | #121 |
| 5 | Qwen 3 VL 32B Instruct | 84.5 | #276 |
| 6 | Qwen 3 VL 32B (Thinking) | 83.4 | #287 (Qwen 3 VL 32B) |
| 7 | Qwen 3 VL 235B A22B Instruct | 81.3 | #264 |
| 8 | Qwen 3 VL 235B A22B (Thinking) | 80.5 | #228 (Qwen 3 VL 235B A22B) |
| 9 | GPT-4o | 79.3 | #333 |
| 10 | Qwen 3 VL 30B A3B Instruct | 77.2 | #365 |
| 11 | InternVL3-78B | 75.6 | #345 |
| 12 | GLM-4.5V | 73.7 | #339 |
| 13 | Qwen 2.5 VL 7B Instruct | 73.4 | #643 |
| 14 | Qwen 3 VL 4B Instruct | 73.3 | #506 |
| 15 | Qwen 3 VL 30B A3B (Thinking) | 71.5 | #338 (Qwen 3 VL 30B A3B) |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=finmtm-single-choice · How It Works · Data refreshed daily, snapshot 2026-10-11.