Claude Sonnet 4 vs Gemini 2.5 Pro

Every finance benchmark where both have a score (Anthropic and Google). Data refreshed 2 Nov 2026.

Shared benchmarks
2
Claude Sonnet 4 only
1
Gemini 2.5 Pro only
3

Shared benchmarks, side by side

Each benchmark is drawn on its own scale. Bars are not comparable across rows.

  • Claude Sonnet 4
  • Gemini 2.5 Pro
Benchmark
Claude Sonnet 4
Gemini 2.5 Pro

7 benchmarks, 2 scored for both. Bold marks the better score where both have one.

Advanced Financial Reasoning at Scale (CFA Level III evaluation)overall % (mean of MCQ and essay), higher is better
73.4
Paper Table 1 (Reported by the authors, 22 Sept 2025)
75.9
Paper Table 1 (Reported by the authors, 22 Sept 2025)
FAITHoverall accuracy %, higher is better
95.6
Paper Table 3 (Reported by the authors, 24 Oct 2025)
91.9
Paper Table 3 (Reported by the authors, 24 Oct 2025)
CAIA (Crypto AI Agent Benchmark)accuracy % (majority vote, 5 runs), higher is better
56.7
Paper Tables 2-3 (Reported by the authors, 17 Jan 2026)
Not scored
Reasoning Models Ace the CFA Exams (CFA mock-exam evaluation)Level I accuracy %, higher is better
Not scored
95.7
Paper Table 5 (Reported by the authors, 9 Dec 2025)
Reasoning Models Ace the CFA Exams (CFA mock-exam evaluation)Level III constructed-response score %, higher is better
Not scored
78.2
Paper Table 5 (Reported by the authors, 9 Dec 2025)
FinDeepResearchoverall accuracy score (0-100), higher is better
Not scored
36.2
OpenFinArena leaderboard (Official board, 15 Oct 2025)
K-FinHallubinary detection F1, higher is better
Not scored
0.849
Paper Table 3 (Reported by the authors, 28 May 2026)

Scores from different benchmarks use different scales and are not added up. Settings can differ between sources; see each leaderboard for details.