Gemini 4 Argon vs Wonder Full in finance

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

Shared benchmarks
4
Gemini 4 Argon only
2
Wonder Full only
0

Shared benchmarks, side by side

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

  • Gemini 4 Argon
  • Wonder Full
  • Excel Modeling Benchmark (EMB) accuracy % (v1.1), higher is better

    Gemini 4 Argon:74.8
    Wonder Full:75 (better)
  • Finance Agent Benchmark Partial Credit accuracy % (v2.1), higher is better

    Gemini 4 Argon:67.7 (better)
    Wonder Full:67.6
  • Vals Finance Index index accuracy %, higher is better

    Gemini 4 Argon:64.9 (better)
    Wonder Full:64.5
  • Tax Agent Bench accuracy % (all-pass x citation factor), higher is better

    Gemini 4 Argon:44.6 (better)
    Wonder Full:43
Benchmark
Gemini 4 Argon
Wonder Full

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

Excel Modeling Benchmark (EMB)accuracy % (v1.1), higher is better
74.8
Vals.ai leaderboard (Official board, 29 Oct 2026)
75
Vals.ai leaderboard (Official board, 29 Oct 2026)
Finance Agent BenchmarkPartial Credit accuracy % (v2.1), higher is better
67.7
Vals.ai leaderboard (Official board, 29 Oct 2026)
67.6
Vals.ai leaderboard (Official board, 29 Oct 2026)
Vals Finance Indexindex accuracy %, higher is better
64.9
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
44.6
Vals.ai leaderboard (Official board, 29 Oct 2026)
43
Vals.ai leaderboard (Official board, 29 Oct 2026)
APEX-AccountingMean Score (% criteria passed), higher is better
71.5
Mercor APEX-Accounting leaderboard (Official board, 1 Nov 2026)
Not scored
Ramp Accounting Benchmean reward % (criteria, mean of 3 attempts), higher is better
61.1
Ramp Labs Accounting Bench (Official board, 14 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.