DeepSeek V4.1 Flash 1017 vs Gemini 4 Carbon
Every finance benchmark where both have a score (DeepSeek and Google). Data refreshed 2 Nov 2026.
- Shared benchmarks
- 2
- DeepSeek V4.1 Flash 1017 only
- 0
- Gemini 4 Carbon only
- 3
Shared benchmarks, side by side
Each benchmark is drawn on its own scale. Bars are not comparable across rows.
- DeepSeek V4.1 Flash 1017
- Gemini 4 Carbon
Vals Finance Index index accuracy %, higher is better
DeepSeek V4.1 Flash 1017:60.9Gemini 4 Carbon:66.3 (better)Tax Agent Bench accuracy % (all-pass x citation factor), higher is better
DeepSeek V4.1 Flash 1017:44.4Gemini 4 Carbon:48.9 (better)
Benchmark
DeepSeek V4.1 Flash 1017
Gemini 4 Carbon
5 benchmarks, 2 scored for both. Bold marks the better score where both have one.
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
Excel Modeling Benchmark (EMB)accuracy %, higher is better
Not scored
Finance Agent BenchmarkPartial Credit accuracy %, 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.
