INVESTORBENCH: leaderboard
Financial decision-making benchmark for investment agents, evaluating portfolio or trading decisions rather than only financial QA.
Metric: Average stock cumulative return (imported). Source: aclanthology.org. Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 72B Instruct | 46.15 | #454 |
| 2 | GPT-4 | 43.7 | #438 |
| 3 | GPT-4o | 39.03 | #343 |
| 4 | Llama 3.1 70B Instruct | 38.95 | #561 |
| 5 | Yi 1.5 34B Chat | 37.97 | #800 |
| 6 | Llama 3.1 8B Instruct | 25.46 | #1035 |
| 7 | Yi-1.5-9B Chat | 22.91 | #1031 |
| 8 | Qwen 2.5 32B Instruct | 20.88 | #498 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=investorbench · How It Works · Data refreshed daily, snapshot 2026-10-20.