FinSearchComp: leaderboard
635 financial search questions from 70 finance professionals on global and Greater China markets: time-sensitive data fetching, historical lookup and historical investigation; ByteDance Seed, 2025.
Metric: Average Score (%). Source: randomtutu.github.io. Status: saturation imminent. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Grok 4 | 68.9 |
| 2 | GPT-5 (Thinking) | 63.9 |
| 3 | Gemini 2.5 Pro | 42.6 |
| 4 | Qwen 3 235B A22B 2507 | 37.4 |
| 5 | Kimi K2 | 29.5 |
| 6 | DeepSeek R1 | 17.2 |
Interactive version: theaggregate.ai/benchmark?slug=finsearchcomp · How It Works · Data refreshed daily, snapshot 2026-09-05.