# Gemini 2.5 Pro finance AI benchmark results

Every finance benchmark score for Gemini 2.5 Pro by Google: 6 benchmarks, each with its rank, metric and source date. Scores are never combined across benchmarks.

## Board standings

Gemini 2.5 Pro is first on 0 benchmarks, top 3 on 4 benchmarks, scored on 6 benchmarks. Places on each benchmark's main board with 2 or more models; scores are never combined. https://benchmarks.finance/method/#standings
- Advanced Financial Reasoning at Scale (CFA Level III evaluation): #3 of 8
- FAITH: #2 of 10
- K-FinHallu: #2 of 10
- Reasoning Models Ace the CFA Exams (CFA mock-exam evaluation): #3 of 6

## Scores

| Benchmark | Rank | Score | Metric | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [FAITH](https://benchmarks.finance/benchmarks/faith/) | 2 of 10 | 91.9 | overall accuracy % | Paper Table 3 | 24 Oct 2025 |
| [K-FinHallu](https://benchmarks.finance/benchmarks/k-finhallu/) | 2 of 10 | 0.849 | binary detection F1 | Paper Table 3 | 28 May 2026 |
| [FinSearchComp](https://benchmarks.finance/benchmarks/finsearchcomp/) | 4 of 11 | 42.6 | Global subset average accuracy % | Paper Table 5 | 16 Sept 2025 |
| [Advanced Financial Reasoning at Scale (CFA Level III evaluation)](https://benchmarks.finance/benchmarks/cfa-level-3-at-scale/) | 3 of 8 | 75.9 | overall % (mean of MCQ and essay) | Paper Table 1 | 22 Sept 2025 |
| [FinDeepResearch](https://benchmarks.finance/benchmarks/findeepresearch/) | 5 of 10 | 36.2 | overall accuracy score (0-100) | OpenFinArena leaderboard | 15 Oct 2025 |
| [Reasoning Models Ace the CFA Exams (CFA mock-exam evaluation)](https://benchmarks.finance/benchmarks/cfa-reasoning-models-ace/) | 3 of 6 | 95.7 | Level I accuracy % | Paper Table 5 | 9 Dec 2025 |

Source: https://benchmarks.finance/models/gemini-2-5-pro/

Created and maintained by Moneda.