Claude Sonnet 5.5 vs DeepSeek V4.1 Flash in finance
Every finance benchmark where both have a score (Anthropic and DeepSeek). Data refreshed 3 Nov 2026.
- Shared benchmarks
- 2
- Claude Sonnet 5.5 only
- 3
- DeepSeek V4.1 Flash only
- 0
Shared benchmarks, side by side
Each benchmark is drawn on its own scale. Bars are not comparable across rows.
- Claude Sonnet 5.5
- DeepSeek V4.1 Flash
Finance Agent Benchmark Partial Credit accuracy % (v2.1), higher is better
Claude Sonnet 5.5:67.3 (better)DeepSeek V4.1 Flash:65.4Visa Agentic Commerce Benchmark pass rate %, higher is better
Claude Sonnet 5.5:64.4 (better)DeepSeek V4.1 Flash:57.8
Benchmark
Claude Sonnet 5.5
DeepSeek V4.1 Flash
5 benchmarks, 2 scored for both. Bold marks the better score where both have one.
Finance Agent BenchmarkPartial Credit accuracy % (v2.1), higher is better
Visa Agentic Commerce Benchmarkpass rate %, higher is better
Excel Modeling Benchmark (EMB)accuracy % (v1.1), higher is better
Not scored
Vals Finance Indexindex accuracy %, higher is better
Not scored
Tax Agent Benchaccuracy % (all-pass x citation factor), 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.