Claude Sonnet 5.5 vs Gemini 4 Argon in finance
Every finance benchmark where both have a score (Anthropic and Google). Data refreshed 2 Nov 2026.
- Shared benchmarks
- 4
- Claude Sonnet 5.5 only
- 0
- Gemini 4 Argon only
- 2
Shared benchmarks, side by side
Each benchmark is drawn on its own scale. Bars are not comparable across rows.
- Claude Sonnet 5.5
- Gemini 4 Argon
Excel Modeling Benchmark (EMB) accuracy % (v1.1), higher is better
Claude Sonnet 5.5:75.9 (better)Gemini 4 Argon:74.8Finance Agent Benchmark Partial Credit accuracy % (v2.1), higher is better
Claude Sonnet 5.5:67.3Gemini 4 Argon:67.7 (better)Vals Finance Index index accuracy %, higher is better
Claude Sonnet 5.5:64.5Gemini 4 Argon:64.9 (better)Tax Agent Bench accuracy % (all-pass x citation factor), higher is better
Claude Sonnet 5.5:42.0Gemini 4 Argon:44.6 (better)
Benchmark
Claude Sonnet 5.5
Gemini 4 Argon
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
Finance Agent BenchmarkPartial Credit accuracy % (v2.1), higher is better
Vals Finance Indexindex accuracy %, higher is better
Tax Agent Benchaccuracy % (all-pass x citation factor), higher is better
APEX-AccountingMean Score (% criteria passed), higher is better
Not scored
Ramp Accounting Benchmean reward % (criteria, mean of 3 attempts), higher is better
Not scored
Scores from different benchmarks use different scales and are not added up. Settings can differ between sources; see each leaderboard for details.