Gemini 3.8 Flash vs GPT-6 Astra in finance

Every finance benchmark where both have a score (Google and OpenAI). Data refreshed 3 Nov 2026.

Shared benchmarks
2
Gemini 3.8 Flash only
2
GPT-6 Astra only
2

Shared benchmarks, side by side

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

  • Gemini 3.8 Flash
  • GPT-6 Astra
Benchmark
Gemini 3.8 Flash
GPT-6 Astra

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

Excel Modeling Benchmark (EMB)accuracy % (v1.1), higher is better
72.9
Vals.ai leaderboard (Official board, 29 Oct 2026)
72.7
Vals.ai leaderboard (Official board, 29 Oct 2026)
Visa Agentic Commerce Benchmarkpass rate %, higher is better
53.3
Visa Research, Oct 2026 snapshot (Official board, 5 Nov 2026)
64.4
Visa Research, Oct 2026 snapshot (Official board, 5 Nov 2026)
APEX-AccountingMean Score (% criteria passed), higher is better
Not scored
64.7
Mercor APEX-Accounting leaderboard (Official board, 1 Nov 2026)
Ramp Accounting Benchmean reward % (criteria, mean of 3 attempts), higher is better
Not scored
48.7
Ramp Labs Accounting Bench (Official board, 5 Sept 2026)
Finance Agent BenchmarkPartial Credit accuracy % (v2.1), higher is better
65.8
Vals.ai leaderboard (Official board, 29 Oct 2026)
Not scored
Vals Finance Indexindex accuracy %, higher is better
60.5
Vals.ai leaderboard (Official board, 29 Oct 2026)
Not scored

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