Gemini 3.8 Flash vs GPT-6 Luna
Same documents, same prompt: where each model gets it right, what it really costs, and how fast it responds.
Verdict
Gemini 3.8 Flash is more accurate; GPT-6 Luna is cheaper in 30 of 30 combinations.
More accurate
Gemini 3.8 Flash
wins 20 of 30
Cheaper
GPT-6 Luna
cheaper in 30 of 30
Faster
Tie
3.0 sec vs 3.2 sec
Fewer fixes
Gemini 3.8 Flash
7 vs 33 documents per 1,000
Across 30 task and document-language combinations (speed and fixes: median).
At a glance
| Accuracy (correct fields) | Per 1,000 documents | |||||
|---|---|---|---|---|---|---|
| Task · documents | Gemini 3.8 Flash | GPT-6 Luna | Difference | Gemini 3.8 Flash | GPT-6 Luna | Difference |
| Invoice extraction | 99.82% | 99.70% | ▼ 0.12 | $3.84 | $0.51 | −87 % |
| Email triage | 98.74% | 97.48% | ▼ 1.26 | $2.39 | $0.13 | −94 % |
| Personal data detection | 99.71% | 99.62% | ▼ 0.09 | $1.86 | $0.11 | −94 % |
| Contract clauses | 99.90% | 99.79% | ▼ 0.11 | $2.47 | $0.20 | −92 % |
| Document summaries | 100.00% | 100.00% | ±0 | $5.46 | $0.16 | −97 % |
| Questions about a document | 99.89% | 99.11% | ▼ 0.78 | $3.00 | $0.15 | −95 % |
| Accuracy (correct fields) | Per 1,000 documents | |||||
|---|---|---|---|---|---|---|
| Task · documents | Gemini 3.8 Flash | GPT-6 Luna | Difference | Gemini 3.8 Flash | GPT-6 Luna | Difference |
| Invoice extraction | 99.95% | 99.28% | ▼ 0.67 | $4.26 | $0.51 | −88 % |
| Email triage | 99.19% | 97.93% | ▼ 1.26 | $3.06 | $0.18 | −94 % |
| Personal data detection | 99.52% | 99.62% | ▲ 0.1 | $2.19 | $0.12 | −95 % |
| Contract clauses | 100.00% | 100.00% | ±0 | $3.09 | $0.27 | −91 % |
| Document summaries | 100.00% | 100.00% | ±0 | $6.69 | $0.21 | −97 % |
| Questions about a document | 100.00% | 100.00% | ±0 | $4.36 | $0.23 | −95 % |
| Accuracy (correct fields) | Per 1,000 documents | |||||
|---|---|---|---|---|---|---|
| Task · documents | Gemini 3.8 Flash | GPT-6 Luna | Difference | Gemini 3.8 Flash | GPT-6 Luna | Difference |
| Invoice extraction | 97.23% | 99.23% | ▲ 2 | $7.15 | $0.54 | −92 % |
| Email triage | 98.37% | 96.96% | ▼ 1.41 | $2.74 | $0.15 | −94 % |
| Personal data detection | 99.71% | 99.62% | ▼ 0.09 | $2.12 | $0.12 | −94 % |
| Contract clauses | 99.90% | 100.00% | ▲ 0.1 | $3.42 | $0.27 | −92 % |
| Document summaries | 100.00% | 100.00% | ±0 | $6.11 | $0.19 | −97 % |
| Questions about a document | 100.00% | 98.00% | ▼ 2 | $3.76 | $0.20 | −95 % |
| Accuracy (correct fields) | Per 1,000 documents | |||||
|---|---|---|---|---|---|---|
| Task · documents | Gemini 3.8 Flash | GPT-6 Luna | Difference | Gemini 3.8 Flash | GPT-6 Luna | Difference |
| Invoice extraction | 97.28% | 99.13% | ▲ 1.85 | $7.84 | $0.55 | −93 % |
| Email triage | 98.96% | 96.81% | ▼ 2.15 | $3.30 | $0.16 | −95 % |
| Personal data detection | 99.81% | 99.71% | ▼ 0.1 | $2.11 | $0.12 | −94 % |
| Contract clauses | 100.00% | 100.00% | ±0 | $3.33 | $0.26 | −92 % |
| Document summaries | 100.00% | 97.00% | ▼ 3 | $6.78 | $0.19 | −97 % |
| Questions about a document | 100.00% | 99.67% | ▼ 0.33 | $4.05 | $0.19 | −95 % |
| Accuracy (correct fields) | Per 1,000 documents | |||||
|---|---|---|---|---|---|---|
| Task · documents | Gemini 3.8 Flash | GPT-6 Luna | Difference | Gemini 3.8 Flash | GPT-6 Luna | Difference |
| Invoice extraction | 99.95% | 99.08% | ▼ 0.87 | $6.07 | $0.56 | −91 % |
| Email triage | 98.59% | 97.26% | ▼ 1.33 | $2.63 | $0.16 | −94 % |
| Personal data detection | 99.81% | 99.62% | ▼ 0.19 | $2.13 | $0.12 | −94 % |
| Contract clauses | 100.00% | 99.33% | ▼ 0.67 | $3.50 | $0.27 | −92 % |
| Document summaries | 100.00% | 98.78% | ▼ 1.22 | $7.06 | $0.20 | −97 % |
| Questions about a document | 100.00% | 99.56% | ▼ 0.44 | $4.06 | $0.20 | −95 % |
Difference: GPT-6 Luna vs. Gemini 3.8 Flash; accuracy in percentage points, price in percent. The better value is in bold. Click a task to see the details.
Invoice extraction · English (US) (150 documents)
Gemini 3.8 Flash is more accurate by 0.1 pp. GPT-6 Luna is 7.6× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 99.82% | 99.70% |
| Error-free documents | 98.00% | 96.67% |
| Per 1,000 documents | $3.84 | $0.51 |
| To fix / 1,000 | 20 | 33 |
| Speed (median) | 3.2 sec | 3.4 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Invoice extraction · Czech (150 documents)
Gemini 3.8 Flash is more accurate by 0.7 pp. GPT-6 Luna is 8.4× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 99.95% | 99.28% |
| Error-free documents | 99.33% | 93.33% |
| Per 1,000 documents | $4.26 | $0.51 |
| To fix / 1,000 | 7 | 67 |
| Speed (median) | 3.5 sec | 3.2 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Invoice extraction · German (150 documents)
GPT-6 Luna is more accurate by 2 pp. GPT-6 Luna is 13.1× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 97.23% | 99.23% |
| Error-free documents | 96.00% | 91.33% |
| Per 1,000 documents | $7.15 | $0.54 |
| To fix / 1,000 | 40 | 87 |
| Speed (median) | 4.7 sec | 3.7 sec |
| Valid answers | 97.33% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Invoice extraction · Spanish (150 documents)
GPT-6 Luna is more accurate by 1.8 pp. GPT-6 Luna is 14.2× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 97.28% | 99.13% |
| Error-free documents | 96.67% | 88.67% |
| Per 1,000 documents | $7.84 | $0.55 |
| To fix / 1,000 | 33 | 113 |
| Speed (median) | 5.7 sec | 3.9 sec |
| Valid answers | 97.33% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Invoice extraction · French (150 documents)
Gemini 3.8 Flash is more accurate by 0.9 pp. GPT-6 Luna is 10.9× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 99.95% | 99.08% |
| Error-free documents | 99.33% | 88.00% |
| Per 1,000 documents | $6.07 | $0.56 |
| To fix / 1,000 | 7 | 120 |
| Speed (median) | 5.3 sec | 3.9 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Email triage · English (US) (150 documents)
Gemini 3.8 Flash is more accurate by 1.3 pp. GPT-6 Luna is 17.7× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 98.74% | 97.48% |
| Error-free documents | 88.67% | 77.33% |
| Per 1,000 documents | $2.39 | $0.13 |
| To fix / 1,000 | 113 | 227 |
| Speed (median) | 2.2 sec | 2.5 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Email triage · Czech (150 documents)
Gemini 3.8 Flash is more accurate by 1.3 pp. GPT-6 Luna is 17.2× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 99.19% | 97.93% |
| Error-free documents | 92.67% | 81.33% |
| Per 1,000 documents | $3.06 | $0.18 |
| To fix / 1,000 | 73 | 187 |
| Speed (median) | 2.6 sec | 2.6 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Email triage · German (150 documents)
Gemini 3.8 Flash is more accurate by 1.4 pp. GPT-6 Luna is 18× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 98.37% | 96.96% |
| Error-free documents | 85.33% | 72.67% |
| Per 1,000 documents | $2.74 | $0.15 |
| To fix / 1,000 | 147 | 273 |
| Speed (median) | 2.9 sec | 2.8 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Email triage · Spanish (150 documents)
Gemini 3.8 Flash is more accurate by 2.2 pp. GPT-6 Luna is 20.9× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 98.96% | 96.81% |
| Error-free documents | 90.67% | 72.00% |
| Per 1,000 documents | $3.30 | $0.16 |
| To fix / 1,000 | 93 | 280 |
| Speed (median) | 3.3 sec | 3.1 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Email triage · French (150 documents)
Gemini 3.8 Flash is more accurate by 1.3 pp. GPT-6 Luna is 16.4× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 98.59% | 97.26% |
| Error-free documents | 87.33% | 76.00% |
| Per 1,000 documents | $2.63 | $0.16 |
| To fix / 1,000 | 127 | 240 |
| Speed (median) | 2.7 sec | 2.8 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Personal data detection · English (US) (150 documents)
Gemini 3.8 Flash is more accurate by 0.1 pp. GPT-6 Luna is 17.6× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 99.71% | 99.62% |
| Error-free documents | 98.00% | 97.33% |
| Per 1,000 documents | $1.86 | $0.11 |
| To fix / 1,000 | 20 | 27 |
| Speed (median) | 1.9 sec | 1.8 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Personal data detection · Czech (150 documents)
GPT-6 Luna is more accurate by 0.1 pp. GPT-6 Luna is 18.3× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 99.52% | 99.62% |
| Error-free documents | 96.67% | 97.33% |
| Per 1,000 documents | $2.19 | $0.12 |
| To fix / 1,000 | 33 | 27 |
| Speed (median) | 2.0 sec | 1.8 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Personal data detection · German (150 documents)
Gemini 3.8 Flash is more accurate by 0.1 pp. GPT-6 Luna is 18.1× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 99.71% | 99.62% |
| Error-free documents | 98.00% | 97.33% |
| Per 1,000 documents | $2.12 | $0.12 |
| To fix / 1,000 | 20 | 27 |
| Speed (median) | 2.3 sec | 2.2 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Personal data detection · Spanish (150 documents)
Gemini 3.8 Flash is more accurate by 0.1 pp. GPT-6 Luna is 17.8× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 99.81% | 99.71% |
| Error-free documents | 98.67% | 98.00% |
| Per 1,000 documents | $2.11 | $0.12 |
| To fix / 1,000 | 13 | 20 |
| Speed (median) | 2.3 sec | 2.3 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Personal data detection · French (150 documents)
Gemini 3.8 Flash is more accurate by 0.2 pp. GPT-6 Luna is 17.2× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 99.81% | 99.62% |
| Error-free documents | 98.67% | 97.33% |
| Per 1,000 documents | $2.13 | $0.12 |
| To fix / 1,000 | 13 | 27 |
| Speed (median) | 2.3 sec | 2.4 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Contract clauses · English (US) (150 documents)
Gemini 3.8 Flash is more accurate by 0.1 pp. GPT-6 Luna is 12.3× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 99.90% | 99.79% |
| Error-free documents | 99.33% | 98.67% |
| Per 1,000 documents | $2.47 | $0.20 |
| To fix / 1,000 | 7 | 13 |
| Speed (median) | 2.0 sec | 2.7 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Contract clauses · Czech (150 documents)
Both are equally accurate. GPT-6 Luna is 11.4× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 100.00% | 100.00% |
| Error-free documents | 100.00% | 100.00% |
| Per 1,000 documents | $3.09 | $0.27 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 2.2 sec | 2.6 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Contract clauses · German (150 documents)
GPT-6 Luna is more accurate by 0.1 pp. GPT-6 Luna is 12.8× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 99.90% | 100.00% |
| Error-free documents | 99.33% | 100.00% |
| Per 1,000 documents | $3.42 | $0.27 |
| To fix / 1,000 | 7 | 0 |
| Speed (median) | 2.6 sec | 3.0 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Contract clauses · Spanish (150 documents)
Both are equally accurate. GPT-6 Luna is 12.6× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 100.00% | 100.00% |
| Error-free documents | 100.00% | 100.00% |
| Per 1,000 documents | $3.33 | $0.26 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 3.0 sec | 3.1 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Contract clauses · French (150 documents)
Gemini 3.8 Flash is more accurate by 0.7 pp. GPT-6 Luna is 12.8× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 100.00% | 99.33% |
| Error-free documents | 100.00% | 91.33% |
| Per 1,000 documents | $3.50 | $0.27 |
| To fix / 1,000 | 0 | 87 |
| Speed (median) | 3.0 sec | 3.2 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Document summaries · English (US) (150 documents)
Both are equally accurate. GPT-6 Luna is 34.2× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 100.00% | 100.00% |
| Error-free documents | 100.00% | 100.00% |
| Per 1,000 documents | $5.46 | $0.16 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 5.4 sec | 2.9 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Document summaries · Czech (150 documents)
Both are equally accurate. GPT-6 Luna is 31.5× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 100.00% | 100.00% |
| Error-free documents | 100.00% | 100.00% |
| Per 1,000 documents | $6.69 | $0.21 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 6.2 sec | 3.4 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Document summaries · German (150 documents)
Both are equally accurate. GPT-6 Luna is 31.5× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 100.00% | 100.00% |
| Error-free documents | 100.00% | 100.00% |
| Per 1,000 documents | $6.11 | $0.19 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 5.8 sec | 3.3 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Document summaries · Spanish (150 documents)
Gemini 3.8 Flash is more accurate by 3 pp. GPT-6 Luna is 35.9× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 100.00% | 97.00% |
| Error-free documents | 100.00% | 82.00% |
| Per 1,000 documents | $6.78 | $0.19 |
| To fix / 1,000 | 0 | 180 |
| Speed (median) | 5.9 sec | 3.0 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Document summaries · French (150 documents)
Gemini 3.8 Flash is more accurate by 1.2 pp. GPT-6 Luna is 36× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 100.00% | 98.78% |
| Error-free documents | 100.00% | 92.67% |
| Per 1,000 documents | $7.06 | $0.20 |
| To fix / 1,000 | 0 | 73 |
| Speed (median) | 6.7 sec | 3.2 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Questions about a document · English (US) (150 documents)
Gemini 3.8 Flash is more accurate by 0.8 pp. GPT-6 Luna is 19.6× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 99.89% | 99.11% |
| Error-free documents | 99.33% | 96.00% |
| Per 1,000 documents | $3.00 | $0.15 |
| To fix / 1,000 | 7 | 40 |
| Speed (median) | 3.0 sec | 3.1 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Questions about a document · Czech (150 documents)
Both are equally accurate. GPT-6 Luna is 19.2× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 100.00% | 100.00% |
| Error-free documents | 100.00% | 100.00% |
| Per 1,000 documents | $4.36 | $0.23 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 3.6 sec | 3.1 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Questions about a document · German (150 documents)
Gemini 3.8 Flash is more accurate by 2 pp. GPT-6 Luna is 18.7× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 100.00% | 98.00% |
| Error-free documents | 100.00% | 91.33% |
| Per 1,000 documents | $3.76 | $0.20 |
| To fix / 1,000 | 0 | 87 |
| Speed (median) | 3.2 sec | 3.2 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Questions about a document · Spanish (150 documents)
Gemini 3.8 Flash is more accurate by 0.3 pp. GPT-6 Luna is 20.8× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 100.00% | 99.67% |
| Error-free documents | 100.00% | 98.67% |
| Per 1,000 documents | $4.05 | $0.19 |
| To fix / 1,000 | 0 | 13 |
| Speed (median) | 3.6 sec | 2.9 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Questions about a document · French (150 documents)
Gemini 3.8 Flash is more accurate by 0.4 pp. GPT-6 Luna is 19.9× cheaper.
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Correct fields | 100.00% | 99.56% |
| Error-free documents | 100.00% | 98.00% |
| Per 1,000 documents | $4.06 | $0.20 |
| To fix / 1,000 | 0 | 20 |
| Speed (median) | 3.7 sec | 3.0 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.