Claude Opus 4.1 vs GPT-4.1 in finance

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

Shared benchmarks
2
Claude Opus 4.1 only
1
GPT-4.1 only
2

Shared benchmarks, side by side

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

  • Claude Opus 4.1
  • GPT-4.1

  • CAIA (Crypto AI Agent Benchmark) accuracy % (majority vote, 5 runs), higher is better

    Claude Opus 4.1:56.3 (better)
    GPT-4.1:46.6

  • LiveTradeBench cumulative return %, higher is better

    Claude Opus 4.1:3.7
    GPT-4.1:6.3 (better)
Benchmark
Claude Opus 4.1
GPT-4.1

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

CAIA (Crypto AI Agent Benchmark)accuracy % (majority vote, 5 runs), higher is better
56.3
Paper Tables 2-3 (Reported by the authors, 17 Jan 2026)
46.6
Paper Tables 2-3 (Reported by the authors, 17 Jan 2026)
LiveTradeBenchcumulative return %, higher is better
3.7
Paper Table 2 (Reported by the authors, 5 Nov 2025)
6.3
Paper Table 2 (Reported by the authors, 5 Nov 2025)
Reasoning Models Ace the CFA Exams (CFA mock-exam evaluation)Level I accuracy %, higher is better
94.6
Paper Table 5 (Reported by the authors, 9 Dec 2025)
Not scored
Reasoning Models Ace the CFA Exams (CFA mock-exam evaluation)Level III constructed-response score %, higher is better
73.4
Paper Table 5 (Reported by the authors, 9 Dec 2025)
Not scored
FAITHoverall accuracy %, higher is better
Not scored
89.2
Paper Table 3 (Reported by the authors, 24 Oct 2025)
FinTrustsafety harmfulness score (1-10, GPT-4.1 mini judge), lower is better
Not scored
7.4
Paper Table 7 (App. A.2) (Reported by the authors, 17 Oct 2025)

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