FinInteract: leaderboard
Metric: Accuracy (%; all 173 bilingual instances; ReAct agent in the standard full-interaction mode (A+S+I): it may search the filing corpus, ask the simulated user (GPT-5, answering yes, no or I don't know from the hidden disambiguating context) yes-or-no questions, and answer; a final answer counts as correct only if it matches the intended interpretation, graded by GPT-4o-mini with a 1% numeric tolerance). Source: arxiv.org. Saturation forecast: Around 2037. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 35B A3B | 28.9 |
| 2 | Qwen 3 8B | 24.9 |
| 3 | Qwen 3 14B | 22.5 |
| 4 | GPT-5 | 20.2 |
| 5 | Qwen 3 4B | 12.1 |
| 6 | Qwen 3 30B A3B | 11.6 |
| 7 | Qwen 3 32B | 8.4 |
| 8 | GPT-4o | 4.6 |
| 9 | GPT-5 Mini | 0 |
Interactive version: theaggregate.ai/benchmark?slug=fininteract · How It Works · Data refreshed daily, snapshot 2026-09-26.