# OpenAI vs Perplexity

Every finance benchmark where both have a score (OpenAI and Perplexity). Data refreshed 2 Nov 2026. Scores from different benchmarks use different scales and are not added up.

| Benchmark | Metric | OpenAI | OpenAI source | Perplexity | Perplexity source | Ahead |
| --- | --- | --- | --- | --- | --- | --- |
| Deep FinResearch Bench | overall factual claim rate % (higher is better) | 86 | Paper Table 7, 22 Apr 2026, https://arxiv.org/html/2604.21006v1 | 75.6 | Paper Table 7, 22 Apr 2026, https://arxiv.org/html/2604.21006v1 | OpenAI |
| Deep FinResearch Bench | qualitative overall (1-4, GPT-5 judge) (higher is better) | 2.0 | Paper Table 3, 22 Apr 2026, https://arxiv.org/html/2604.21006v1 | 2.1 | Paper Table 3, 22 Apr 2026, https://arxiv.org/html/2604.21006v1 | Perplexity |
| FinResearchBench | Final Score (0-100) (higher is better) | 74.2 | Paper Table 1, 20 Oct 2025, https://arxiv.org/html/2507.16248v3 | 67.0 | Paper Table 1, 20 Oct 2025, https://arxiv.org/html/2507.16248v3 | OpenAI |

Source: https://benchmarks.finance/compare/openai-vs-perplexity/

Created and maintained by Moneda.