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: xpert.bytedance.com. Source: randomtutu.github.io. Saturation forecast: Around January 2027. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Grok 4 | 68.9 | #181 |
| 2 | GPT-5 (Thinking) | 63.9 | #98 (GPT-5) |
| 3 | Gemini 2.5 Pro | 42.6 | #152 |
| 4 | Qwen 3 235B A22B 2507 | 37.4 | #260 |
| 5 | Kimi K2 | 29.5 | #243 |
| 6 | DeepSeek R1 | 17.2 | #251 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=finsearchcomp · How It Works · Data refreshed daily, snapshot 2026-10-20.