gemini-3.1-pro vs GPT 5.5

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

Shared benchmarks
2
gemini-3.1-pro only
0
GPT 5.5 only
1

Shared benchmarks, side by side

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

  • gemini-3.1-pro
  • GPT 5.5

  • BlueFin criteria-weighted score % (overall), higher is better

    gemini-3.1-pro:45.9
    GPT 5.5:49.6 (better)

  • KTD-Fin total return %, higher is better

    gemini-3.1-pro:8.3
    GPT 5.5:61.3 (better)
Benchmark
gemini-3.1-pro
GPT 5.5

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

BlueFincriteria-weighted score % (overall), higher is better
45.9
Paper Table 2 (Reported by the authors, May 2026)
49.6
Paper Table 2 (Reported by the authors, May 2026)
KTD-Fintotal return %, higher is better
8.3
Paper Table 4 (Reported by the authors, 27 May 2026)
61.3
Paper Table 4 (Reported by the authors, 27 May 2026)
CorpFin v2accuracy %, higher is better
Not scored
68.4
Vals.ai leaderboard (archived) (Official board, 12 Aug 2026)

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