ModelVerdict

Comparison

DeepSeek V4.1 Flash vs GPT-6 Luna

Same documents, same prompt: where each model is right, what it really costs and how fast it answers.

At a glance

Task · documentsEnglish (US)CzechGermanSpanishFrench
Invoice extraction99.4% / 99.7%99.9% / 99.3%99.5% / 99.2%98.3% / 99.1%99.4% / 98.9%
Email triage97.6% / 97.5%97.4% / 97.9%96.3% / 97.0%——
Personal data detection99.6% / 99.6%99.7% / 99.6%99.8% / 99.6%——
Contract clauses100.0% / 99.8%100.0% / 100.0%97.2% / 100.0%——

Correct fields: DeepSeek V4.1 Flash / GPT-6 Luna; the better one in bold. Click a cell to see the details.

Invoice extraction · English (US) (150 documents)

GPT-6 Luna is more accurate by 0.3 pp.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields99.4%99.7%
Error-free documents93%97%
Per 1,000 documents$0.52$0.51
To fix / 1,0006733
Speed (median)5.7 sec3.4 sec
Valid answers100.0%100.0%

Accuracy per field

FieldDeepSeek V4.1 FlashGPT-6 Luna
Supplier100.0%100.0%
Supplier ID (EIN, IČO…)100.0%100.0%
Invoice number100.0%99.3%
Payment reference96.7%98.0%
Invoice date100.0%100.0%
Due date100.0%100.0%
Net by tax rate100.0%100.0%
Tax by rate100.0%100.0%
Total100.0%100.0%
Currency99.3%100.0%
Bank account97.3%99.3%

Documents where they differ

Invoice extraction · Czech (150 documents)

DeepSeek V4.1 Flash is more accurate by 0.6 pp.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields99.9%99.3%
Error-free documents99%93%
Per 1,000 documents$0.50$0.51
To fix / 1,0001367
Speed (median)5.0 sec3.2 sec
Valid answers100.0%100.0%

Accuracy per field

FieldDeepSeek V4.1 FlashGPT-6 Luna
Supplier99.3%95.3%
Supplier ID (EIN, IČO…)100.0%98.7%
VAT ID100.0%98.0%
Invoice number100.0%100.0%
Payment reference100.0%100.0%
Invoice date100.0%100.0%
Tax point100.0%100.0%
Due date100.0%99.3%
Net by tax rate100.0%100.0%
Tax by rate100.0%100.0%
Total100.0%100.0%
Currency100.0%100.0%
Bank account99.3%99.3%

Documents where they differ

Invoice extraction · German (150 documents)

DeepSeek V4.1 Flash is more accurate by 0.3 pp.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields99.5%99.2%
Error-free documents94%91%
Per 1,000 documents$0.57$0.54
To fix / 1,0006087
Speed (median)6.4 sec3.7 sec
Valid answers100.0%100.0%

Accuracy per field

FieldDeepSeek V4.1 FlashGPT-6 Luna
Supplier99.3%100.0%
Supplier ID (EIN, IČO…)98.7%98.7%
VAT ID99.3%99.3%
Invoice number100.0%99.3%
Payment reference100.0%100.0%
Invoice date100.0%98.7%
Tax point99.3%100.0%
Due date99.3%100.0%
Net by tax rate100.0%100.0%
Tax by rate100.0%100.0%
Total100.0%100.0%
Currency100.0%100.0%
Bank account98.0%94.0%

Documents where they differ

Invoice extraction · Spanish (79 documents)

GPT-6 Luna is more accurate by 0.8 pp. GPT-6 Luna is 1.3× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields98.3%99.1%
Error-free documents77%88%
Per 1,000 documents$0.71$0.55
To fix / 1,000228120
Speed (median)5.8 sec3.9 sec
Valid answers100.0%100.0%

Accuracy per field

FieldDeepSeek V4.1 FlashGPT-6 Luna
Supplier93.7%99.0%
Supplier ID (EIN, IČO…)100.0%100.0%
VAT ID100.0%100.0%
Invoice number100.0%100.0%
Payment reference97.5%98.0%
Invoice date100.0%100.0%
Tax point98.7%100.0%
Due date100.0%100.0%
Net by tax rate88.6%100.0%
Tax by rate100.0%100.0%
Total100.0%100.0%
Currency100.0%100.0%
Bank account98.7%91.0%

Documents where they differ

Invoice extraction · French (74 documents)

DeepSeek V4.1 Flash is more accurate by 0.5 pp. GPT-6 Luna is 1.1× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields99.4%98.9%
Error-free documents92%86%
Per 1,000 documents$0.65$0.57
To fix / 1,00081143
Speed (median)5.7 sec3.8 sec
Valid answers100.0%100.0%

Accuracy per field

FieldDeepSeek V4.1 FlashGPT-6 Luna
Supplier100.0%99.0%
Supplier ID (EIN, IČO…)100.0%99.0%
VAT ID98.7%98.0%
Invoice number100.0%99.0%
Payment reference98.7%100.0%
Invoice date100.0%100.0%
Tax point100.0%100.0%
Due date100.0%100.0%
Net by tax rate100.0%100.0%
Tax by rate100.0%100.0%
Total100.0%100.0%
Currency100.0%100.0%
Bank account94.6%90.8%

Documents where they differ

Email triage · English (US) (150 documents)

DeepSeek V4.1 Flash is more accurate by 0.1 pp. GPT-6 Luna is 1.7× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields97.6%97.5%
Error-free documents79%77%
Per 1,000 documents$0.23$0.13
To fix / 1,000213227
Speed (median)3.8 sec2.5 sec
Valid answers100.0%100.0%

Accuracy per field

FieldDeepSeek V4.1 FlashGPT-6 Luna
Category100.0%100.0%
Priority96.7%98.0%
Sentiment82.0%79.3%
Customer name100.0%100.0%
Order number100.0%100.0%
Invoice number100.0%100.0%
Amount100.0%100.0%
Currency100.0%100.0%
Deadline100.0%100.0%

Documents where they differ

  • Omar Cabrera · Email · DeepSeek V4.1 Flash 9/9, GPT-6 Luna 8/9
  • Russell Bates · Email · DeepSeek V4.1 Flash 8/9, GPT-6 Luna 9/9
  • Laurie Knight · Email · DeepSeek V4.1 Flash 9/9, GPT-6 Luna 8/9
  • Cody Baldwin · Email · DeepSeek V4.1 Flash 9/9, GPT-6 Luna 8/9
  • Allison Floyd · Email · DeepSeek V4.1 Flash 9/9, GPT-6 Luna 8/9
  • Scott Davis · Email · DeepSeek V4.1 Flash 9/9, GPT-6 Luna 8/9
  • Sandra Hogan · Email · DeepSeek V4.1 Flash 9/9, GPT-6 Luna 8/9
  • Robert Lewis · Email · DeepSeek V4.1 Flash 8/9, GPT-6 Luna 9/9

Email triage · Czech (150 documents)

GPT-6 Luna is more accurate by 0.5 pp. GPT-6 Luna is 1.7× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields97.4%97.9%
Error-free documents77%81%
Per 1,000 documents$0.30$0.18
To fix / 1,000227187
Speed (median)4.2 sec2.6 sec
Valid answers100.0%100.0%

Accuracy per field

FieldDeepSeek V4.1 FlashGPT-6 Luna
Category100.0%100.0%
Priority98.7%98.7%
Sentiment78.0%82.7%
Customer name100.0%100.0%
Order number100.0%100.0%
Invoice number100.0%100.0%
Amount100.0%100.0%
Currency100.0%100.0%
Deadline100.0%100.0%

Documents where they differ

Email triage · German (145 documents)

GPT-6 Luna is more accurate by 0.6 pp. GPT-6 Luna is 2× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields96.3%97.0%
Error-free documents68%73%
Per 1,000 documents$0.30$0.15
To fix / 1,000324273
Speed (median)4.2 sec2.8 sec
Valid answers100.0%100.0%

Accuracy per field

FieldDeepSeek V4.1 FlashGPT-6 Luna
Category100.0%100.0%
Priority97.2%99.3%
Sentiment69.7%73.3%
Customer name100.0%100.0%
Order number100.0%100.0%
Invoice number100.0%100.0%
Amount100.0%100.0%
Currency100.0%100.0%
Deadline100.0%100.0%

Documents where they differ

Personal data detection · English (US) (150 documents)

Both are equally accurate. GPT-6 Luna is 2.7× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields99.6%99.6%
Error-free documents97%97%
Per 1,000 documents$0.29$0.11
To fix / 1,0002727
Speed (median)3.8 sec1.8 sec
Valid answers100.0%100.0%

Accuracy per field

FieldDeepSeek V4.1 FlashGPT-6 Luna
Names98.7%98.7%
Email addresses100.0%100.0%
Phone numbers100.0%100.0%
Addresses98.7%98.7%
Dates of birth100.0%100.0%
National IDs100.0%100.0%
Bank accounts100.0%100.0%

Documents where they differ

Personal data detection · Czech (150 documents)

DeepSeek V4.1 Flash is more accurate by 0.1 pp. GPT-6 Luna is 2.6× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields99.7%99.6%
Error-free documents98%97%
Per 1,000 documents$0.31$0.12
To fix / 1,0002027
Speed (median)4.2 sec1.8 sec
Valid answers100.0%100.0%

Accuracy per field

FieldDeepSeek V4.1 FlashGPT-6 Luna
Names100.0%100.0%
Email addresses100.0%100.0%
Phone numbers100.0%100.0%
Addresses98.0%97.3%
Dates of birth100.0%100.0%
National IDs100.0%100.0%
Bank accounts100.0%100.0%

Documents where they differ

Personal data detection · German (148 documents)

DeepSeek V4.1 Flash is more accurate by 0.2 pp. GPT-6 Luna is 2.6× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields99.8%99.6%
Error-free documents99%97%
Per 1,000 documents$0.31$0.12
To fix / 1,0001327
Speed (median)3.7 sec2.2 sec
Valid answers100.0%100.0%

Accuracy per field

FieldDeepSeek V4.1 FlashGPT-6 Luna
Names100.0%100.0%
Email addresses100.0%100.0%
Phone numbers100.0%100.0%
Addresses98.7%97.3%
Dates of birth100.0%100.0%
National IDs100.0%100.0%
Bank accounts100.0%100.0%

Documents where they differ

Both models got the same number of fields right on every example document.

Contract clauses · English (US) (150 documents)

DeepSeek V4.1 Flash is more accurate by 0.2 pp. GPT-6 Luna is 1.6× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields100.0%99.8%
Error-free documents100%99%
Per 1,000 documents$0.32$0.20
To fix / 1,000013
Speed (median)3.9 sec2.7 sec
Valid answers100.0%100.0%

Accuracy per field

FieldDeepSeek V4.1 FlashGPT-6 Luna
Provider100.0%98.7%
Provider ID100.0%100.0%
Client100.0%98.7%
Client ID100.0%100.0%
Contract type100.0%100.0%
Price (net)100.0%100.0%
Currency100.0%100.0%
Billing period100.0%100.0%
Effective date100.0%100.0%
End date100.0%100.0%
Notice period (months)100.0%100.0%
Late-payment penalty (% per day)100.0%100.0%
Governing law100.0%100.0%

Documents where they differ

Contract clauses · Czech (150 documents)

Both are equally accurate. GPT-6 Luna is 1.6× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields100.0%100.0%
Error-free documents100%100%
Per 1,000 documents$0.42$0.27
To fix / 1,00000
Speed (median)4.3 sec2.6 sec
Valid answers100.0%100.0%

Accuracy per field

FieldDeepSeek V4.1 FlashGPT-6 Luna
Provider100.0%100.0%
Provider ID100.0%100.0%
Client100.0%100.0%
Client ID100.0%100.0%
Contract type100.0%100.0%
Price (net)100.0%100.0%
Currency100.0%100.0%
Billing period100.0%100.0%
Effective date100.0%100.0%
End date100.0%100.0%
Notice period (months)100.0%100.0%
Late-payment penalty (% per day)100.0%100.0%
Governing law100.0%100.0%

Documents where they differ

Both models got the same number of fields right on every example document.

Contract clauses · German (145 documents)

GPT-6 Luna is more accurate by 2.8 pp. GPT-6 Luna is 1.9× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields97.2%100.0%
Error-free documents77%100%
Per 1,000 documents$0.51$0.27
To fix / 1,0002280
Speed (median)4.6 sec3.0 sec
Valid answers100.0%100.0%

Accuracy per field

FieldDeepSeek V4.1 FlashGPT-6 Luna
Provider100.0%100.0%
Provider ID81.4%100.0%
Client100.0%100.0%
Client ID82.8%100.0%
Contract type100.0%100.0%
Price (net)100.0%100.0%
Currency100.0%100.0%
Billing period100.0%100.0%
Effective date100.0%100.0%
End date100.0%100.0%
Notice period (months)100.0%100.0%
Late-payment penalty (% per day)100.0%100.0%
Governing law100.0%100.0%

Documents where they differ