# Gemini 2.5 Pro vs Llama-3.1-8B

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

| Benchmark | Metric | Gemini 2.5 Pro | Gemini 2.5 Pro source | Llama-3.1-8B | Llama-3.1-8B source | Ahead |
| --- | --- | --- | --- | --- | --- | --- |
| FAITH | overall accuracy % (higher is better) | 91.9 | Paper Table 3, 24 Oct 2025, https://arxiv.org/html/2508.05201v2 | 47.5 | Paper Table 3, 24 Oct 2025, https://arxiv.org/html/2508.05201v2 | Gemini 2.5 Pro |
| K-FinHallu | binary detection F1 (higher is better) | 0.849 | Paper Table 3, 28 May 2026, https://arxiv.org/html/2605.29523v1 | 0.674 | Paper Table 3, 28 May 2026, https://arxiv.org/html/2605.29523v1 | Gemini 2.5 Pro |

Source: https://benchmarks.finance/compare/gemini-2-5-pro-vs-llama-3-1-8b/

Created and maintained by Moneda.