DeepSeek V4.1 Flash 1017 vs Wonder Full in finance

Every finance benchmark where both have a score. Data refreshed 2 Nov 2026.

Shared benchmarks
2
DeepSeek V4.1 Flash 1017 only
0
Wonder Full 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 1017
  • Wonder Full

  • Vals Finance Index index accuracy %, higher is better

    DeepSeek V4.1 Flash 1017:60.9
    Wonder Full:64.5 (better)

  • Tax Agent Bench accuracy % (all-pass x citation factor), higher is better

    DeepSeek V4.1 Flash 1017:44.4 (better)
    Wonder Full:43
Benchmark
DeepSeek V4.1 Flash 1017
Wonder Full

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

Vals Finance Indexindex accuracy %, higher is better
60.9
Vals.ai leaderboard (Official board, 29 Oct 2026)
64.5
Vals.ai leaderboard (Official board, 29 Oct 2026)
Tax Agent Benchaccuracy % (all-pass x citation factor), higher is better
44.4
Vals.ai leaderboard (Official board, 29 Oct 2026)
43
Vals.ai leaderboard (Official board, 29 Oct 2026)
Excel Modeling Benchmark (EMB)accuracy % (v1.1), higher is better
Not scored
75
Vals.ai leaderboard (Official board, 29 Oct 2026)
Finance Agent BenchmarkPartial Credit accuracy % (v2.1), higher is better
Not scored
67.6
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.