DeepSeek V4.1 Flash vs Gemini 3.8 Flash in finance

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

Shared benchmarks
2
DeepSeek V4.1 Flash only
0
Gemini 3.8 Flash only
2

Shared benchmarks, side by side

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

  • DeepSeek V4.1 Flash
  • Gemini 3.8 Flash
Benchmark
DeepSeek V4.1 Flash
Gemini 3.8 Flash

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

Finance Agent BenchmarkPartial Credit accuracy % (v2.1), higher is better
65.4
Vals.ai leaderboard (Official board, 29 Oct 2026)
65.8
Vals.ai leaderboard (Official board, 29 Oct 2026)
Visa Agentic Commerce Benchmarkpass rate %, higher is better
57.8
Visa Research, Oct 2026 snapshot (Official board, 5 Nov 2026)
53.3
Visa Research, Oct 2026 snapshot (Official board, 5 Nov 2026)
Excel Modeling Benchmark (EMB)accuracy % (v1.1), higher is better
Not scored
72.9
Vals.ai leaderboard (Official board, 29 Oct 2026)
Vals Finance Indexindex accuracy %, higher is better
Not scored
60.5
Vals.ai leaderboard (Official board, 29 Oct 2026)

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