ModelVerdict

Comparison

GPT-6 Sol vs Mistral Medium 3.5

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 extraction99.9% / 97.8%99.9% / 93.5%100.0% / 97.4%99.2% / 97.0%99.9% / 98.2%
Email triage99.0% / 94.9%99.0% / 94.5%98.2% / 92.7%——
Personal data detection99.7% / 99.7%99.7% / 99.8%99.7% / 100.0%——
Contract clauses100.0% / 98.1%100.0% / 100.0%100.0% / 97.1%——

Correct fields: GPT-6 Sol / Mistral Medium 3.5; the better one in bold. Click a cell to see the details.

Invoice extraction · English (US) (150 documents)

GPT-6 Sol is more accurate by 2.2 pp. Mistral Medium 3.5 is 2.2× cheaper.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.9%97.8%
Error-free documents99%79%
Per 1,000 documents$9.65$4.37
To fix / 1,0007207
Speed (median)4.1 sec2.3 sec
Valid answers100.0%100.0%

Accuracy per field

FieldGPT-6 SolMistral Medium 3.5
Supplier100.0%100.0%
Supplier ID (EIN, IČO…)100.0%100.0%
Invoice number100.0%100.0%
Payment reference100.0%94.7%
Invoice date100.0%98.7%
Due date100.0%99.3%
Net by tax rate100.0%88.0%
Tax by rate100.0%98.7%
Total100.0%100.0%
Currency100.0%100.0%
Bank account99.3%96.0%

Documents where they differ

Invoice extraction · Czech (150 documents)

GPT-6 Sol is more accurate by 6.4 pp. Mistral Medium 3.5 is 2.2× cheaper.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.9%93.5%
Error-free documents99%63%
Per 1,000 documents$10.12$4.69
To fix / 1,00013367
Speed (median)3.9 sec2.6 sec
Valid answers100.0%100.0%

Accuracy per field

FieldGPT-6 SolMistral Medium 3.5
Supplier99.3%90.0%
Supplier ID (EIN, IČO…)100.0%87.3%
VAT ID100.0%85.3%
Invoice number100.0%99.3%
Payment reference99.3%95.3%
Invoice date100.0%88.7%
Tax point100.0%86.7%
Due date100.0%90.7%
Net by tax rate100.0%99.3%
Tax by rate100.0%98.7%
Total100.0%100.0%
Currency100.0%100.0%
Bank account100.0%94.0%

Documents where they differ

Invoice extraction · German (150 documents)

GPT-6 Sol is more accurate by 2.6 pp. Mistral Medium 3.5 is 2.3× cheaper.

MetricGPT-6 SolMistral Medium 3.5
Correct fields100.0%97.4%
Error-free documents99%75%
Per 1,000 documents$10.65$4.72
To fix / 1,0007253
Speed (median)4.9 sec2.5 sec
Valid answers100.0%100.0%

Accuracy per field

FieldGPT-6 SolMistral Medium 3.5
Supplier100.0%97.3%
Supplier ID (EIN, IČO…)100.0%98.7%
VAT ID100.0%96.0%
Invoice number100.0%100.0%
Payment reference100.0%92.7%
Invoice date100.0%98.0%
Tax point100.0%90.7%
Due date100.0%97.3%
Net by tax rate100.0%98.0%
Tax by rate100.0%100.0%
Total100.0%100.0%
Currency100.0%100.0%
Bank account99.3%97.3%

Documents where they differ

Invoice extraction · Spanish (100 documents)

GPT-6 Sol is more accurate by 2.2 pp. Mistral Medium 3.5 is 2.3× cheaper.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.2%97.0%
Error-free documents89%67%
Per 1,000 documents$10.76$4.75
To fix / 1,000110330
Speed (median)5.7 sec2.5 sec
Valid answers100.0%100.0%

Accuracy per field

FieldGPT-6 SolMistral Medium 3.5
Supplier98.0%99.0%
Supplier ID (EIN, IČO…)100.0%100.0%
VAT ID100.0%94.0%
Invoice number100.0%100.0%
Payment reference100.0%93.0%
Invoice date100.0%100.0%
Tax point100.0%93.0%
Due date100.0%97.0%
Net by tax rate92.0%85.0%
Tax by rate100.0%100.0%
Total100.0%100.0%
Currency100.0%100.0%
Bank account99.0%100.0%

Documents where they differ

Invoice extraction · French (100 documents)

GPT-6 Sol is more accurate by 1.8 pp. Mistral Medium 3.5 is 2.3× cheaper.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.9%98.2%
Error-free documents99%81%
Per 1,000 documents$11.05$4.81
To fix / 1,00010190
Speed (median)5.9 sec2.6 sec
Valid answers100.0%100.0%

Accuracy per field

FieldGPT-6 SolMistral Medium 3.5
Supplier100.0%99.0%
Supplier ID (EIN, IČO…)100.0%99.0%
VAT ID100.0%98.0%
Invoice number100.0%100.0%
Payment reference99.0%94.0%
Invoice date100.0%100.0%
Tax point100.0%100.0%
Due date100.0%100.0%
Net by tax rate100.0%95.0%
Tax by rate100.0%98.0%
Total100.0%99.0%
Currency100.0%96.0%
Bank account100.0%98.0%

Documents where they differ

Email triage · English (US) (150 documents)

GPT-6 Sol is more accurate by 4.1 pp. Mistral Medium 3.5 is 1.7× cheaper.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.0%94.9%
Error-free documents92%57%
Per 1,000 documents$2.44$1.47
To fix / 1,00080427
Speed (median)2.8 sec0.8 sec
Valid answers100.0%100.0%

Accuracy per field

FieldGPT-6 SolMistral Medium 3.5
Category100.0%100.0%
Priority98.0%63.3%
Sentiment93.3%90.7%
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 · Czech (150 documents)

GPT-6 Sol is more accurate by 4.4 pp. Mistral Medium 3.5 is 1.6× cheaper.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.0%94.5%
Error-free documents91%55%
Per 1,000 documents$3.19$1.95
To fix / 1,00093447
Speed (median)2.8 sec0.8 sec
Valid answers100.0%100.0%

Accuracy per field

FieldGPT-6 SolMistral Medium 3.5
Category100.0%100.0%
Priority98.0%63.3%
Sentiment92.7%87.3%
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

Email triage · German (150 documents)

GPT-6 Sol is more accurate by 5.5 pp. Mistral Medium 3.5 is 1.5× cheaper.

MetricGPT-6 SolMistral Medium 3.5
Correct fields98.2%92.7%
Error-free documents84%48%
Per 1,000 documents$2.73$1.77
To fix / 1,000160520
Speed (median)2.9 sec0.8 sec
Valid answers100.0%100.0%

Accuracy per field

FieldGPT-6 SolMistral Medium 3.5
Category100.0%100.0%
Priority97.3%56.7%
Sentiment86.7%78.0%
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. Mistral Medium 3.5 is 1.8× cheaper.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.7%99.7%
Error-free documents98%98%
Per 1,000 documents$2.09$1.15
To fix / 1,0002020
Speed (median)2.6 sec0.8 sec
Valid answers100.0%100.0%

Accuracy per field

FieldGPT-6 SolMistral Medium 3.5
Names100.0%99.3%
Email addresses100.0%100.0%
Phone numbers100.0%100.0%
Addresses98.0%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)

Mistral Medium 3.5 is more accurate by 0.1 pp. Mistral Medium 3.5 is 1.6× cheaper.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.7%99.8%
Error-free documents98%99%
Per 1,000 documents$2.22$1.40
To fix / 1,0002013
Speed (median)2.5 sec0.8 sec
Valid answers100.0%100.0%

Accuracy per field

FieldGPT-6 SolMistral Medium 3.5
Names100.0%98.7%
Email addresses100.0%100.0%
Phone numbers100.0%100.0%
Addresses98.0%100.0%
Dates of birth100.0%100.0%
National IDs100.0%100.0%
Bank accounts100.0%100.0%

Documents where they differ

Personal data detection · German (150 documents)

Mistral Medium 3.5 is more accurate by 0.3 pp. Mistral Medium 3.5 is 1.5× cheaper.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.7%100.0%
Error-free documents98%100%
Per 1,000 documents$2.13$1.38
To fix / 1,000200
Speed (median)2.6 sec0.9 sec
Valid answers100.0%100.0%

Accuracy per field

FieldGPT-6 SolMistral Medium 3.5
Names100.0%100.0%
Email addresses100.0%100.0%
Phone numbers100.0%100.0%
Addresses98.0%100.0%
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)

GPT-6 Sol is more accurate by 1.9 pp. Mistral Medium 3.5 is 1.4× cheaper.

MetricGPT-6 SolMistral Medium 3.5
Correct fields100.0%98.1%
Error-free documents100%87%
Per 1,000 documents$3.33$2.35
To fix / 1,0000127
Speed (median)2.5 sec1.1 sec
Valid answers100.0%100.0%

Accuracy per field

FieldGPT-6 SolMistral Medium 3.5
Provider100.0%87.3%
Provider ID100.0%100.0%
Client100.0%88.7%
Client ID100.0%99.3%
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. Mistral Medium 3.5 is 1.5× cheaper.

MetricGPT-6 SolMistral Medium 3.5
Correct fields100.0%100.0%
Error-free documents100%100%
Per 1,000 documents$4.62$3.06
To fix / 1,00000
Speed (median)2.0 sec1.2 sec
Valid answers100.0%100.0%

Accuracy per field

FieldGPT-6 SolMistral Medium 3.5
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 (150 documents)

GPT-6 Sol is more accurate by 2.9 pp. Mistral Medium 3.5 is 1.6× cheaper.

MetricGPT-6 SolMistral Medium 3.5
Correct fields100.0%97.1%
Error-free documents100%75%
Per 1,000 documents$4.36$2.76
To fix / 1,0000247
Speed (median)2.9 sec1.2 sec
Valid answers100.0%100.0%

Accuracy per field

FieldGPT-6 SolMistral Medium 3.5
Provider100.0%100.0%
Provider ID100.0%82.0%
Client100.0%100.0%
Client ID100.0%80.7%
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