GPT-6 Luna vs Mistral Large 4
Same documents, same prompt: where each model gets it right, what it really costs, and how fast it responds.
Verdict
GPT-6 Luna is more accurate and cheaper in 30 of 30 combinations.
More accurate
GPT-6 Luna
wins 19 of 30
Cheaper
GPT-6 Luna
cheaper in 30 of 30
Faster
GPT-6 Luna
3.0 sec vs 31.5 sec
Fewer fixes
GPT-6 Luna
33 vs 107 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 | GPT-6 Luna | Mistral Large 4 | Difference | GPT-6 Luna | Mistral Large 4 | Difference |
| Invoice extraction | 99.70% | 95.39% | ▼ 4.31 | $0.51 | $6.65 | +1210 % |
| Email triage | 97.48% | 98.74% | ▲ 1.26 | $0.13 | $3.52 | +2511 % |
| Personal data detection | 99.62% | 99.62% | ±0 | $0.11 | $2.89 | +2632 % |
| Contract clauses | 99.79% | 96.10% | ▼ 3.69 | $0.20 | $5.24 | +2507 % |
| Document summaries | 100.00% | 100.00% | ±0 | $0.16 | $5.62 | +3427 % |
| Questions about a document | 99.11% | 98.89% | ▼ 0.22 | $0.15 | $4.16 | +2624 % |
| Accuracy (correct fields) | Per 1,000 documents | |||||
|---|---|---|---|---|---|---|
| Task · documents | GPT-6 Luna | Mistral Large 4 | Difference | GPT-6 Luna | Mistral Large 4 | Difference |
| Invoice extraction | 99.28% | 97.08% | ▼ 2.2 | $0.51 | $5.69 | +1026 % |
| Email triage | 97.93% | 98.15% | ▲ 0.22 | $0.18 | $4.41 | +2377 % |
| Personal data detection | 99.62% | 99.33% | ▼ 0.29 | $0.12 | $3.15 | +2538 % |
| Contract clauses | 100.00% | 100.00% | ±0 | $0.27 | $4.58 | +1596 % |
| Document summaries | 100.00% | 83.33% | ▼ 16.67 | $0.21 | $10.72 | +4944 % |
| Questions about a document | 100.00% | 89.89% | ▼ 10.11 | $0.23 | $7.08 | +3016 % |
| Accuracy (correct fields) | Per 1,000 documents | |||||
|---|---|---|---|---|---|---|
| Task · documents | GPT-6 Luna | Mistral Large 4 | Difference | GPT-6 Luna | Mistral Large 4 | Difference |
| Invoice extraction | 99.23% | 97.49% | ▼ 1.74 | $0.54 | $6.72 | +1133 % |
| Email triage | 96.96% | 97.85% | ▲ 0.89 | $0.15 | $3.78 | +2381 % |
| Personal data detection | 99.62% | 99.52% | ▼ 0.1 | $0.12 | $2.61 | +2124 % |
| Contract clauses | 100.00% | 99.44% | ▼ 0.56 | $0.27 | $5.12 | +1823 % |
| Document summaries | 100.00% | 99.33% | ▼ 0.67 | $0.19 | $7.19 | +3609 % |
| Questions about a document | 98.00% | 93.56% | ▼ 4.44 | $0.20 | $5.77 | +2772 % |
| Accuracy (correct fields) | Per 1,000 documents | |||||
|---|---|---|---|---|---|---|
| Task · documents | GPT-6 Luna | Mistral Large 4 | Difference | GPT-6 Luna | Mistral Large 4 | Difference |
| Invoice extraction | 99.13% | 96.51% | ▼ 2.62 | $0.55 | $7.49 | +1255 % |
| Email triage | 96.81% | 97.93% | ▲ 1.12 | $0.16 | $4.03 | +2455 % |
| Personal data detection | 99.71% | 99.81% | ▲ 0.1 | $0.12 | $3.16 | +2566 % |
| Contract clauses | 100.00% | 100.00% | ±0 | $0.26 | $4.83 | +1730 % |
| Document summaries | 97.00% | 91.33% | ▼ 5.67 | $0.19 | $7.99 | +4133 % |
| Questions about a document | 99.67% | 94.22% | ▼ 5.45 | $0.19 | $5.74 | +2847 % |
| Accuracy (correct fields) | Per 1,000 documents | |||||
|---|---|---|---|---|---|---|
| Task · documents | GPT-6 Luna | Mistral Large 4 | Difference | GPT-6 Luna | Mistral Large 4 | Difference |
| Invoice extraction | 99.08% | 88.97% | ▼ 10.11 | $0.56 | $8.71 | +1461 % |
| Email triage | 97.26% | 98.30% | ▲ 1.04 | $0.16 | $3.70 | +2211 % |
| Personal data detection | 99.62% | 98.67% | ▼ 0.95 | $0.12 | $2.96 | +2282 % |
| Contract clauses | 99.33% | 99.28% | ▼ 0.05 | $0.27 | $4.60 | +1584 % |
| Document summaries | 98.78% | 72.67% | ▼ 26.11 | $0.20 | $11.26 | +5632 % |
| Questions about a document | 99.56% | 92.33% | ▼ 7.23 | $0.20 | $5.74 | +2712 % |
Difference: Mistral Large 4 vs. GPT-6 Luna; 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)
GPT-6 Luna is more accurate by 4.3 pp. GPT-6 Luna is 13.1× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 99.70% | 95.39% |
| Error-free documents | 96.67% | 77.33% |
| Per 1,000 documents | $0.51 | $6.65 |
| To fix / 1,000 | 33 | 227 |
| Speed (median) | 3.4 sec | 29.0 sec |
| Valid answers | 100.00% | 97.33% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Invoice extraction · Czech (150 documents)
GPT-6 Luna is more accurate by 2.2 pp. GPT-6 Luna is 11.3× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 99.28% | 97.08% |
| Error-free documents | 93.33% | 88.67% |
| Per 1,000 documents | $0.51 | $5.69 |
| To fix / 1,000 | 67 | 113 |
| Speed (median) | 3.2 sec | 26.3 sec |
| Valid answers | 100.00% | 98.00% |
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 1.7 pp. GPT-6 Luna is 12.3× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 99.23% | 97.49% |
| Error-free documents | 91.33% | 91.33% |
| Per 1,000 documents | $0.54 | $6.72 |
| To fix / 1,000 | 87 | 87 |
| Speed (median) | 3.7 sec | 35.3 sec |
| Valid answers | 100.00% | 98.00% |
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 2.6 pp. GPT-6 Luna is 13.5× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 99.13% | 96.51% |
| Error-free documents | 88.67% | 88.00% |
| Per 1,000 documents | $0.55 | $7.49 |
| To fix / 1,000 | 113 | 120 |
| Speed (median) | 3.9 sec | 41.3 sec |
| Valid answers | 100.00% | 97.33% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Invoice extraction · French (150 documents)
GPT-6 Luna is more accurate by 10.1 pp. GPT-6 Luna is 15.6× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 99.08% | 88.97% |
| Error-free documents | 88.00% | 65.33% |
| Per 1,000 documents | $0.56 | $8.71 |
| To fix / 1,000 | 120 | 347 |
| Speed (median) | 3.9 sec | 43.4 sec |
| Valid answers | 100.00% | 91.33% |
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)
Mistral Large 4 is more accurate by 1.3 pp. GPT-6 Luna is 26.1× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 97.48% | 98.74% |
| Error-free documents | 77.33% | 88.67% |
| Per 1,000 documents | $0.13 | $3.52 |
| To fix / 1,000 | 227 | 113 |
| Speed (median) | 2.5 sec | 19.8 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 · Czech (150 documents)
Mistral Large 4 is more accurate by 0.2 pp. GPT-6 Luna is 24.8× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 97.93% | 98.15% |
| Error-free documents | 81.33% | 89.33% |
| Per 1,000 documents | $0.18 | $4.41 |
| To fix / 1,000 | 187 | 107 |
| Speed (median) | 2.6 sec | 28.4 sec |
| Valid answers | 100.00% | 99.33% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Email triage · German (150 documents)
Mistral Large 4 is more accurate by 0.9 pp. GPT-6 Luna is 24.8× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 96.96% | 97.85% |
| Error-free documents | 72.67% | 82.00% |
| Per 1,000 documents | $0.15 | $3.78 |
| To fix / 1,000 | 273 | 180 |
| Speed (median) | 2.8 sec | 21.7 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.
Email triage · Spanish (150 documents)
Mistral Large 4 is more accurate by 1.1 pp. GPT-6 Luna is 25.5× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 96.81% | 97.93% |
| Error-free documents | 72.00% | 82.00% |
| Per 1,000 documents | $0.16 | $4.03 |
| To fix / 1,000 | 280 | 180 |
| Speed (median) | 3.1 sec | 25.4 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.
Email triage · French (150 documents)
Mistral Large 4 is more accurate by 1 pp. GPT-6 Luna is 23.1× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 97.26% | 98.30% |
| Error-free documents | 76.00% | 84.67% |
| Per 1,000 documents | $0.16 | $3.70 |
| To fix / 1,000 | 240 | 153 |
| Speed (median) | 2.8 sec | 24.5 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.
Personal data detection · English (US) (150 documents)
Both are equally accurate. GPT-6 Luna is 27.3× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 99.62% | 99.62% |
| Error-free documents | 97.33% | 97.33% |
| Per 1,000 documents | $0.11 | $2.89 |
| To fix / 1,000 | 27 | 27 |
| Speed (median) | 1.8 sec | 28.2 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 · Czech (150 documents)
GPT-6 Luna is more accurate by 0.3 pp. GPT-6 Luna is 26.4× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 99.62% | 99.33% |
| Error-free documents | 97.33% | 95.33% |
| Per 1,000 documents | $0.12 | $3.15 |
| To fix / 1,000 | 27 | 47 |
| Speed (median) | 1.8 sec | 18.5 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.
Personal data detection · German (150 documents)
GPT-6 Luna is more accurate by 0.1 pp. GPT-6 Luna is 22.2× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 99.62% | 99.52% |
| Error-free documents | 97.33% | 96.67% |
| Per 1,000 documents | $0.12 | $2.61 |
| To fix / 1,000 | 27 | 33 |
| Speed (median) | 2.2 sec | 18.6 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.
Personal data detection · Spanish (150 documents)
Mistral Large 4 is more accurate by 0.1 pp. GPT-6 Luna is 26.7× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 99.71% | 99.81% |
| Error-free documents | 98.00% | 98.67% |
| Per 1,000 documents | $0.12 | $3.16 |
| To fix / 1,000 | 20 | 13 |
| Speed (median) | 2.3 sec | 21.9 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.
Personal data detection · French (150 documents)
GPT-6 Luna is more accurate by 0.9 pp. GPT-6 Luna is 23.8× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 99.62% | 98.67% |
| Error-free documents | 97.33% | 94.67% |
| Per 1,000 documents | $0.12 | $2.96 |
| To fix / 1,000 | 27 | 53 |
| Speed (median) | 2.4 sec | 23.6 sec |
| Valid answers | 100.00% | 99.33% |
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)
GPT-6 Luna is more accurate by 3.7 pp. GPT-6 Luna is 26.1× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 99.79% | 96.10% |
| Error-free documents | 98.67% | 74.67% |
| Per 1,000 documents | $0.20 | $5.24 |
| To fix / 1,000 | 13 | 253 |
| Speed (median) | 2.7 sec | 41.4 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 · Czech (150 documents)
Both are equally accurate. GPT-6 Luna is 17× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 100.00% | 100.00% |
| Error-free documents | 100.00% | 100.00% |
| Per 1,000 documents | $0.27 | $4.58 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 2.6 sec | 43.9 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.
Contract clauses · German (150 documents)
GPT-6 Luna is more accurate by 0.6 pp. GPT-6 Luna is 19.2× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 100.00% | 99.44% |
| Error-free documents | 100.00% | 95.33% |
| Per 1,000 documents | $0.27 | $5.12 |
| To fix / 1,000 | 0 | 47 |
| Speed (median) | 3.0 sec | 36.2 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.
Contract clauses · Spanish (150 documents)
Both are equally accurate. GPT-6 Luna is 18.3× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 100.00% | 100.00% |
| Error-free documents | 100.00% | 100.00% |
| Per 1,000 documents | $0.26 | $4.83 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 3.1 sec | 35.0 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 · French (150 documents)
Both are equally accurate. GPT-6 Luna is 16.8× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 99.33% | 99.28% |
| Error-free documents | 91.33% | 90.67% |
| Per 1,000 documents | $0.27 | $4.60 |
| To fix / 1,000 | 87 | 93 |
| Speed (median) | 3.2 sec | 34.7 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.
Document summaries · English (US) (150 documents)
Both are equally accurate. GPT-6 Luna is 35.3× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 100.00% | 100.00% |
| Error-free documents | 100.00% | 100.00% |
| Per 1,000 documents | $0.16 | $5.62 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 2.9 sec | 37.2 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 · Czech (150 documents)
GPT-6 Luna is more accurate by 16.7 pp. GPT-6 Luna is 50.4× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 100.00% | 83.33% |
| Error-free documents | 100.00% | 83.33% |
| Per 1,000 documents | $0.21 | $10.72 |
| To fix / 1,000 | 0 | 167 |
| Speed (median) | 3.4 sec | 55.4 sec |
| Valid answers | 100.00% | 83.33% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Document summaries · German (150 documents)
GPT-6 Luna is more accurate by 0.7 pp. GPT-6 Luna is 37.1× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 100.00% | 99.33% |
| Error-free documents | 100.00% | 99.33% |
| Per 1,000 documents | $0.19 | $7.19 |
| To fix / 1,000 | 0 | 7 |
| Speed (median) | 3.3 sec | 48.0 sec |
| Valid answers | 100.00% | 99.33% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Document summaries · Spanish (150 documents)
GPT-6 Luna is more accurate by 5.7 pp. GPT-6 Luna is 42.3× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 97.00% | 91.33% |
| Error-free documents | 82.00% | 91.33% |
| Per 1,000 documents | $0.19 | $7.99 |
| To fix / 1,000 | 180 | 87 |
| Speed (median) | 3.0 sec | 38.3 sec |
| Valid answers | 100.00% | 91.33% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Document summaries · French (150 documents)
GPT-6 Luna is more accurate by 26.1 pp. GPT-6 Luna is 57.3× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 98.78% | 72.67% |
| Error-free documents | 92.67% | 72.67% |
| Per 1,000 documents | $0.20 | $11.26 |
| To fix / 1,000 | 73 | 273 |
| Speed (median) | 3.2 sec | 46.4 sec |
| Valid answers | 100.00% | 72.67% |
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)
GPT-6 Luna is more accurate by 0.2 pp. GPT-6 Luna is 27.2× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 99.11% | 98.89% |
| Error-free documents | 96.00% | 97.33% |
| Per 1,000 documents | $0.15 | $4.16 |
| To fix / 1,000 | 40 | 27 |
| Speed (median) | 3.1 sec | 17.7 sec |
| Valid answers | 100.00% | 99.33% |
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)
GPT-6 Luna is more accurate by 10.1 pp. GPT-6 Luna is 31.2× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 100.00% | 89.89% |
| Error-free documents | 100.00% | 78.00% |
| Per 1,000 documents | $0.23 | $7.08 |
| To fix / 1,000 | 0 | 220 |
| Speed (median) | 3.1 sec | 33.6 sec |
| Valid answers | 100.00% | 93.33% |
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)
GPT-6 Luna is more accurate by 4.4 pp. GPT-6 Luna is 28.7× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 98.00% | 93.56% |
| Error-free documents | 91.33% | 89.33% |
| Per 1,000 documents | $0.20 | $5.77 |
| To fix / 1,000 | 87 | 107 |
| Speed (median) | 3.2 sec | 31.5 sec |
| Valid answers | 100.00% | 94.67% |
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)
GPT-6 Luna is more accurate by 5.4 pp. GPT-6 Luna is 29.5× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 99.67% | 94.22% |
| Error-free documents | 98.67% | 90.67% |
| Per 1,000 documents | $0.19 | $5.74 |
| To fix / 1,000 | 13 | 93 |
| Speed (median) | 2.9 sec | 22.8 sec |
| Valid answers | 100.00% | 95.33% |
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)
GPT-6 Luna is more accurate by 7.2 pp. GPT-6 Luna is 28.1× cheaper.
| Metric | GPT-6 Luna | Mistral Large 4 |
|---|---|---|
| Correct fields | 99.56% | 92.33% |
| Error-free documents | 98.00% | 87.33% |
| Per 1,000 documents | $0.20 | $5.74 |
| To fix / 1,000 | 20 | 127 |
| Speed (median) | 3.0 sec | 19.8 sec |
| Valid answers | 100.00% | 94.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.