Gemini 3.8 Flash vs GPT-6 Sol
Same documents, same prompt: where each model is right, what it really costs and how fast it answers.
At a glance
| Task · documents | English (US) | Czech | German | Spanish | French |
|---|---|---|---|---|---|
| Invoice extraction | 99.8% / 99.9% | 100.0% / 99.9% | 97.2% / 100.0% | 95.9% / 99.2% | 99.9% / 99.9% |
| Email triage | 98.7% / 99.0% | 99.2% / 99.0% | 98.4% / 98.2% | — | — |
| Personal data detection | 99.7% / 99.7% | 99.5% / 99.7% | 99.7% / 99.7% | — | — |
| Contract clauses | 99.9% / 100.0% | 100.0% / 100.0% | 99.9% / 100.0% | — | — |
Correct fields: Gemini 3.8 Flash / GPT-6 Sol; 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 0.1 pp. Gemini 3.8 Flash is 2.5× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Correct fields | 99.8% | 99.9% |
| Error-free documents | 98% | 99% |
| Per 1,000 documents | $3.84 | $9.65 |
| To fix / 1,000 | 20 | 7 |
| Speed (median) | 3.2 sec | 4.1 sec |
| Valid answers | 100.0% | 100.0% |
Accuracy per field
| Field | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Supplier | 100.0% | 100.0% |
| Supplier ID (EIN, IČO…) | 100.0% | 100.0% |
| Invoice number | 100.0% | 100.0% |
| Payment reference | 100.0% | 100.0% |
| Invoice date | 100.0% | 100.0% |
| Due date | 100.0% | 100.0% |
| Net by tax rate | 100.0% | 100.0% |
| Tax by rate | 100.0% | 100.0% |
| Total | 100.0% | 100.0% |
| Currency | 100.0% | 100.0% |
| Bank account | 98.0% | 99.3% |
Documents where they differ
- Rose Lowery · INV-14797 · Clean image · Gemini 3.8 Flash 10/11, GPT-6 Sol 11/11
Invoice extraction · Czech (150 documents)
Gemini 3.8 Flash is more accurate by 0.1 pp. Gemini 3.8 Flash is 2.4× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Correct fields | 100.0% | 99.9% |
| Error-free documents | 99% | 99% |
| Per 1,000 documents | $4.26 | $10.12 |
| To fix / 1,000 | 7 | 13 |
| Speed (median) | 3.5 sec | 3.9 sec |
| Valid answers | 100.0% | 100.0% |
Accuracy per field
| Field | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Supplier | 99.3% | 99.3% |
| Supplier ID (EIN, IČO…) | 100.0% | 100.0% |
| VAT ID | 100.0% | 100.0% |
| Invoice number | 100.0% | 100.0% |
| Payment reference | 100.0% | 99.3% |
| Invoice date | 100.0% | 100.0% |
| Tax point | 100.0% | 100.0% |
| Due date | 100.0% | 100.0% |
| Net by tax rate | 100.0% | 100.0% |
| Tax by rate | 100.0% | 100.0% |
| Total | 100.0% | 100.0% |
| Currency | 100.0% | 100.0% |
| Bank account | 100.0% | 100.0% |
Documents where they differ
Both models got the same number of fields right on every example document.
Invoice extraction · German (150 documents)
GPT-6 Sol is more accurate by 2.7 pp. Gemini 3.8 Flash is 1.5× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Correct fields | 97.2% | 100.0% |
| Error-free documents | 96% | 99% |
| Per 1,000 documents | $7.15 | $10.65 |
| To fix / 1,000 | 40 | 7 |
| Speed (median) | 4.7 sec | 4.9 sec |
| Valid answers | 97.3% | 100.0% |
Accuracy per field
| Field | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Supplier | 97.3% | 100.0% |
| Supplier ID (EIN, IČO…) | 97.3% | 100.0% |
| VAT ID | 96.7% | 100.0% |
| Invoice number | 97.3% | 100.0% |
| Payment reference | 97.3% | 100.0% |
| Invoice date | 97.3% | 100.0% |
| Tax point | 97.3% | 100.0% |
| Due date | 97.3% | 100.0% |
| Net by tax rate | 96.7% | 100.0% |
| Tax by rate | 97.3% | 100.0% |
| Total | 97.3% | 100.0% |
| Currency | 97.3% | 100.0% |
| Bank account | 97.3% | 99.3% |
Documents where they differ
- Gebäudereinigung Klara Weiß · 2025-1126 · PDF text · Gemini 3.8 Flash 0/13, GPT-6 Sol 13/13
Invoice extraction · Spanish (100 documents)
GPT-6 Sol is more accurate by 3.2 pp. Gemini 3.8 Flash is 1.4× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Correct fields | 95.9% | 99.2% |
| Error-free documents | 95% | 89% |
| Per 1,000 documents | $7.86 | $10.76 |
| To fix / 1,000 | 50 | 110 |
| Speed (median) | 5.3 sec | 5.7 sec |
| Valid answers | 96.0% | 100.0% |
Accuracy per field
| Field | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Supplier | 95.0% | 98.0% |
| Supplier ID (EIN, IČO…) | 96.0% | 100.0% |
| VAT ID | 96.0% | 100.0% |
| Invoice number | 96.0% | 100.0% |
| Payment reference | 96.0% | 100.0% |
| Invoice date | 96.0% | 100.0% |
| Tax point | 96.0% | 100.0% |
| Due date | 96.0% | 100.0% |
| Net by tax rate | 96.0% | 92.0% |
| Tax by rate | 96.0% | 100.0% |
| Total | 96.0% | 100.0% |
| Currency | 96.0% | 100.0% |
| Bank account | 96.0% | 99.0% |
Documents where they differ
- Climatización Levante S.L. · F2025-1305 · Scan · Gemini 3.8 Flash 0/13, GPT-6 Sol 12/13
- Leyre Lladó Vall · F2025-1476 · Photo · Gemini 3.8 Flash 13/13, GPT-6 Sol 12/13
- Escobar Comunicación S.L. · RECT-2025-0924 · Clean image · Gemini 3.8 Flash 13/13, GPT-6 Sol 12/13
Invoice extraction · French (100 documents)
Both are equally accurate. Gemini 3.8 Flash is 1.8× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Correct fields | 99.9% | 99.9% |
| Error-free documents | 99% | 99% |
| Per 1,000 documents | $6.18 | $11.05 |
| To fix / 1,000 | 10 | 10 |
| Speed (median) | 5.2 sec | 5.9 sec |
| Valid answers | 100.0% | 100.0% |
Accuracy per field
| Field | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Supplier | 100.0% | 100.0% |
| Supplier ID (EIN, IČO…) | 100.0% | 100.0% |
| VAT ID | 100.0% | 100.0% |
| Invoice number | 100.0% | 100.0% |
| Payment reference | 99.0% | 99.0% |
| Invoice date | 100.0% | 100.0% |
| Tax point | 100.0% | 100.0% |
| Due date | 100.0% | 100.0% |
| Net by tax rate | 100.0% | 100.0% |
| Tax by rate | 100.0% | 100.0% |
| Total | 100.0% | 100.0% |
| Currency | 100.0% | 100.0% |
| Bank account | 100.0% | 100.0% |
Documents where they differ
Both models got the same number of fields right on every example document.
Email triage · English (US) (150 documents)
GPT-6 Sol is more accurate by 0.3 pp.
| Metric | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Correct fields | 98.7% | 99.0% |
| Error-free documents | 89% | 92% |
| Per 1,000 documents | $2.39 | $2.44 |
| To fix / 1,000 | 113 | 80 |
| Speed (median) | 2.2 sec | 2.8 sec |
| Valid answers | 100.0% | 100.0% |
Accuracy per field
| Field | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Category | 100.0% | 100.0% |
| Priority | 100.0% | 98.0% |
| Sentiment | 88.7% | 93.3% |
| Customer name | 100.0% | 100.0% |
| Order number | 100.0% | 100.0% |
| Invoice number | 100.0% | 100.0% |
| Amount | 100.0% | 100.0% |
| Currency | 100.0% | 100.0% |
| Deadline | 100.0% | 100.0% |
Documents where they differ
- Laurie Knight · Email · Gemini 3.8 Flash 8/9, GPT-6 Sol 9/9
Email triage · Czech (150 documents)
Gemini 3.8 Flash is more accurate by 0.2 pp.
| Metric | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Correct fields | 99.2% | 99.0% |
| Error-free documents | 93% | 91% |
| Per 1,000 documents | $3.06 | $3.19 |
| To fix / 1,000 | 73 | 93 |
| Speed (median) | 2.6 sec | 2.8 sec |
| Valid answers | 100.0% | 100.0% |
Accuracy per field
| Field | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Category | 100.0% | 100.0% |
| Priority | 99.3% | 98.0% |
| Sentiment | 93.3% | 92.7% |
| Customer name | 100.0% | 100.0% |
| Order number | 100.0% | 100.0% |
| Invoice number | 100.0% | 100.0% |
| Amount | 100.0% | 100.0% |
| Currency | 100.0% | 100.0% |
| Deadline | 100.0% | 100.0% |
Documents where they differ
Both models got the same number of fields right on every example document.
Email triage · German (150 documents)
Gemini 3.8 Flash is more accurate by 0.2 pp.
| Metric | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Correct fields | 98.4% | 98.2% |
| Error-free documents | 85% | 84% |
| Per 1,000 documents | $2.74 | $2.73 |
| To fix / 1,000 | 147 | 160 |
| Speed (median) | 2.9 sec | 2.9 sec |
| Valid answers | 100.0% | 100.0% |
Accuracy per field
| Field | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Category | 100.0% | 100.0% |
| Priority | 100.0% | 97.3% |
| Sentiment | 85.3% | 86.7% |
| Customer name | 100.0% | 100.0% |
| Order number | 100.0% | 100.0% |
| Invoice number | 100.0% | 100.0% |
| Amount | 100.0% | 100.0% |
| Currency | 100.0% | 100.0% |
| Deadline | 100.0% | 100.0% |
Documents where they differ
- Friedbert Hoffmann · Email · Gemini 3.8 Flash 9/9, GPT-6 Sol 8/9
Personal data detection · English (US) (150 documents)
Both are equally accurate. Gemini 3.8 Flash is 1.1× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Correct fields | 99.7% | 99.7% |
| Error-free documents | 98% | 98% |
| Per 1,000 documents | $1.86 | $2.09 |
| To fix / 1,000 | 20 | 20 |
| Speed (median) | 1.9 sec | 2.6 sec |
| Valid answers | 100.0% | 100.0% |
Accuracy per field
| Field | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Names | 100.0% | 100.0% |
| Email addresses | 100.0% | 100.0% |
| Phone numbers | 100.0% | 100.0% |
| Addresses | 98.0% | 98.0% |
| Dates of birth | 100.0% | 100.0% |
| National IDs | 100.0% | 100.0% |
| Bank accounts | 100.0% | 100.0% |
Documents where they differ
Both models got the same number of fields right on every example document.
Personal data detection · Czech (150 documents)
GPT-6 Sol is more accurate by 0.2 pp.
| Metric | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Correct fields | 99.5% | 99.7% |
| Error-free documents | 97% | 98% |
| Per 1,000 documents | $2.19 | $2.22 |
| To fix / 1,000 | 33 | 20 |
| Speed (median) | 2.0 sec | 2.5 sec |
| Valid answers | 100.0% | 100.0% |
Accuracy per field
| Field | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Names | 98.7% | 100.0% |
| Email addresses | 100.0% | 100.0% |
| Phone numbers | 100.0% | 100.0% |
| Addresses | 98.0% | 98.0% |
| Dates of birth | 100.0% | 100.0% |
| National IDs | 100.0% | 100.0% |
| Bank accounts | 100.0% | 100.0% |
Documents where they differ
Both models got the same number of fields right on every example document.
Personal data detection · German (150 documents)
Both are equally accurate.
| Metric | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Correct fields | 99.7% | 99.7% |
| Error-free documents | 98% | 98% |
| Per 1,000 documents | $2.12 | $2.13 |
| To fix / 1,000 | 20 | 20 |
| Speed (median) | 2.3 sec | 2.6 sec |
| Valid answers | 100.0% | 100.0% |
Accuracy per field
| Field | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Names | 100.0% | 100.0% |
| Email addresses | 100.0% | 100.0% |
| Phone numbers | 100.0% | 100.0% |
| Addresses | 98.0% | 98.0% |
| Dates of birth | 100.0% | 100.0% |
| National IDs | 100.0% | 100.0% |
| Bank accounts | 100.0% | 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 0.1 pp. Gemini 3.8 Flash is 1.4× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Correct fields | 99.9% | 100.0% |
| Error-free documents | 99% | 100% |
| Per 1,000 documents | $2.47 | $3.33 |
| To fix / 1,000 | 7 | 0 |
| Speed (median) | 2.0 sec | 2.5 sec |
| Valid answers | 100.0% | 100.0% |
Accuracy per field
| Field | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Provider | 99.3% | 100.0% |
| Provider ID | 100.0% | 100.0% |
| Client | 99.3% | 100.0% |
| Client ID | 100.0% | 100.0% |
| Contract type | 100.0% | 100.0% |
| Price (net) | 100.0% | 100.0% |
| Currency | 100.0% | 100.0% |
| Billing period | 100.0% | 100.0% |
| Effective date | 100.0% | 100.0% |
| End date | 100.0% | 100.0% |
| Notice period (months) | 100.0% | 100.0% |
| Late-payment penalty (% per day) | 100.0% | 100.0% |
| Governing law | 100.0% | 100.0% |
Documents where they differ
- Kim Electric Co. · Ramos & Sons, Co. · Contract text · Gemini 3.8 Flash 11/13, GPT-6 Sol 13/13
Contract clauses · Czech (150 documents)
Both are equally accurate. Gemini 3.8 Flash is 1.5× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Correct fields | 100.0% | 100.0% |
| Error-free documents | 100% | 100% |
| Per 1,000 documents | $3.09 | $4.62 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 2.2 sec | 2.0 sec |
| Valid answers | 100.0% | 100.0% |
Accuracy per field
| Field | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Provider | 100.0% | 100.0% |
| Provider ID | 100.0% | 100.0% |
| Client | 100.0% | 100.0% |
| Client ID | 100.0% | 100.0% |
| Contract type | 100.0% | 100.0% |
| Price (net) | 100.0% | 100.0% |
| Currency | 100.0% | 100.0% |
| Billing period | 100.0% | 100.0% |
| Effective date | 100.0% | 100.0% |
| End date | 100.0% | 100.0% |
| Notice period (months) | 100.0% | 100.0% |
| Late-payment penalty (% per day) | 100.0% | 100.0% |
| Governing law | 100.0% | 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 0.1 pp. Gemini 3.8 Flash is 1.3× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Correct fields | 99.9% | 100.0% |
| Error-free documents | 99% | 100% |
| Per 1,000 documents | $3.42 | $4.36 |
| To fix / 1,000 | 7 | 0 |
| Speed (median) | 2.6 sec | 2.9 sec |
| Valid answers | 100.0% | 100.0% |
Accuracy per field
| Field | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| Provider | 100.0% | 100.0% |
| Provider ID | 99.3% | 100.0% |
| Client | 100.0% | 100.0% |
| Client ID | 99.3% | 100.0% |
| Contract type | 100.0% | 100.0% |
| Price (net) | 100.0% | 100.0% |
| Currency | 100.0% | 100.0% |
| Billing period | 100.0% | 100.0% |
| Effective date | 100.0% | 100.0% |
| End date | 100.0% | 100.0% |
| Notice period (months) | 100.0% | 100.0% |
| Late-payment penalty (% per day) | 100.0% | 100.0% |
| Governing law | 100.0% | 100.0% |
Documents where they differ
Both models got the same number of fields right on every example document.