Leaderboard
Reasoning Models Ace the CFA Exams (CFA mock-exam evaluation)
Mock CFA exams at all three levels: multiple choice at Levels I-III, plus constructed-response essays at Level III. Results are judged against CFA pass thresholds.
Best reported
97.6
Gemini 3.0 Pro
Level I accuracy %
9 Dec 2025
Reasoning Models Ace the CFA Exams (CFA mock-exam evaluation) arXiv v1 (2025-12-09)
Level I accuracy %, higher is better. 6 models.
Updated 9 Dec 2025
- Gemini 3.0 Pro97.6
- gpt-596.1
- Gemini 2.5 Pro95.7
- grok-494.8
- Claude Opus 4.194.6
- DeepSeek V3.190.9
Reasoning Models Ace the CFA Exams (CFA mock-exam evaluation) arXiv v1 (2025-12-09)
Level I accuracy %, higher is better. 6 models.
Updated 9 Dec 2025
- 1Gemini 3.0 Pro97.6
- 2gpt-596.1
- 3Gemini 2.5 Pro95.7
- 4grok-494.8
- 5Claude Opus 4.194.6
- 6DeepSeek V3.190.9
| 1 | Gemini 3.0 Pro | 97.6 | zero-shot | Paper Table 5 Reported by the authors, 9 Dec 2025 | |
|---|---|---|---|---|---|
| 2 | gpt-5 | OpenAI | 96.1 | zero-shot | Paper Table 5 Reported by the authors, 9 Dec 2025 |
| 3 | Gemini 2.5 Pro | 95.7 | zero-shot | Paper Table 5 Reported by the authors, 9 Dec 2025 | |
| 4 | grok-4 | xAI | 94.8 | zero-shot | Paper Table 5 Reported by the authors, 9 Dec 2025 |
| 5 | Claude Opus 4.1 | Anthropic | 94.6 | zero-shot | Paper Table 5 Reported by the authors, 9 Dec 2025 |
| 6 | DeepSeek V3.1 | DeepSeek | 90.9 | zero-shot | Paper Table 5 Reported by the authors, 9 Dec 2025 |
Reasoning Models Ace the CFA Exams (CFA mock-exam evaluation) arXiv v1 (2025-12-09)
Level III constructed-response score %, higher is better. 6 models.
Updated 9 Dec 2025
- Gemini 3.0 Pro86.6
- Gemini 2.5 Pro78.2
- Claude Opus 4.173.4
- gpt-571.8
- grok-471.2
- DeepSeek V3.170.8
Reasoning Models Ace the CFA Exams (CFA mock-exam evaluation) arXiv v1 (2025-12-09)
Level III constructed-response score %, higher is better. 6 models.
Updated 9 Dec 2025
- 1Gemini 3.0 Pro86.6
- 2Gemini 2.5 Pro78.2
- 3Claude Opus 4.173.4
- 4gpt-571.8
- 5grok-471.2
- 6DeepSeek V3.170.8
| 1 | Gemini 3.0 Pro | 86.6 | zero-shot, o4-mini grader | Paper Table 5 Reported by the authors, 9 Dec 2025 | |
|---|---|---|---|---|---|
| 2 | Gemini 2.5 Pro | 78.2 | zero-shot, o4-mini grader | Paper Table 5 Reported by the authors, 9 Dec 2025 | |
| 3 | Claude Opus 4.1 | Anthropic | 73.4 | zero-shot, o4-mini grader | Paper Table 5 Reported by the authors, 9 Dec 2025 |
| 4 | gpt-5 | OpenAI | 71.8 | zero-shot, o4-mini grader | Paper Table 5 Reported by the authors, 9 Dec 2025 |
| 5 | grok-4 | xAI | 71.2 | zero-shot, o4-mini grader | Paper Table 5 Reported by the authors, 9 Dec 2025 |
| 6 | DeepSeek V3.1 | DeepSeek | 70.8 | zero-shot, o4-mini grader | Paper Table 5 Reported by the authors, 9 Dec 2025 |
Full details for Reasoning Models Ace the CFA Exams (CFA mock-exam evaluation)