GPT-6 Sol vs Mistral Medium 3.5
Same documents, same prompt: where each model gets it right, what it really costs, and how fast it responds.
Verdict
GPT-6 Sol is more accurate; Mistral Medium 3.5 is cheaper in 30 of 30 combinations.
More accurate
GPT-6 Sol
wins 14 of 30
Cheaper
Mistral Medium 3.5
cheaper in 30 of 30
Faster
Mistral Medium 3.5
1.0 sec vs 2.9 sec
Fewer fixes
GPT-6 Sol
13 vs 20 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 Sol | Mistral Medium 3.5 | Difference | GPT-6 Sol | Mistral Medium 3.5 | Difference |
| Invoice extraction | 99.94% | 97.76% | ▼ 2.18 | $9.65 | $4.37 | −55 % |
| Email triage | 99.04% | 94.89% | ▼ 4.15 | $2.44 | $1.47 | −39 % |
| Personal data detection | 99.71% | 99.71% | ±0 | $2.09 | $1.15 | −45 % |
| Contract clauses | 100.00% | 98.10% | ▼ 1.9 | $3.33 | $2.35 | −29 % |
| Document summaries | 99.56% | 100.00% | ▲ 0.44 | $3.85 | $1.57 | −59 % |
| Questions about a document | 100.00% | 100.00% | ±0 | $2.36 | $1.81 | −23 % |
| Accuracy (correct fields) | Per 1,000 documents | |||||
|---|---|---|---|---|---|---|
| Task · documents | GPT-6 Sol | Mistral Medium 3.5 | Difference | GPT-6 Sol | Mistral Medium 3.5 | Difference |
| Invoice extraction | 99.90% | 93.49% | ▼ 6.41 | $10.12 | $4.69 | −54 % |
| Email triage | 98.96% | 94.52% | ▼ 4.44 | $3.19 | $1.95 | −39 % |
| Personal data detection | 99.71% | 99.81% | ▲ 0.1 | $2.22 | $1.40 | −37 % |
| Contract clauses | 100.00% | 100.00% | ±0 | $4.62 | $3.06 | −34 % |
| Document summaries | 100.00% | 100.00% | ±0 | $4.72 | $2.31 | −51 % |
| Questions about a document | 100.00% | 100.00% | ±0 | $3.95 | $2.51 | −36 % |
| Accuracy (correct fields) | Per 1,000 documents | |||||
|---|---|---|---|---|---|---|
| Task · documents | GPT-6 Sol | Mistral Medium 3.5 | Difference | GPT-6 Sol | Mistral Medium 3.5 | Difference |
| Invoice extraction | 99.95% | 97.38% | ▼ 2.57 | $10.65 | $4.72 | −56 % |
| Email triage | 98.22% | 92.74% | ▼ 5.48 | $2.73 | $1.77 | −35 % |
| Personal data detection | 99.71% | 100.00% | ▲ 0.29 | $2.13 | $1.38 | −35 % |
| Contract clauses | 100.00% | 97.13% | ▼ 2.87 | $4.36 | $2.76 | −37 % |
| Document summaries | 100.00% | 100.00% | ±0 | $4.11 | $1.98 | −52 % |
| Questions about a document | 100.00% | 100.00% | ±0 | $3.23 | $2.13 | −34 % |
| Accuracy (correct fields) | Per 1,000 documents | |||||
|---|---|---|---|---|---|---|
| Task · documents | GPT-6 Sol | Mistral Medium 3.5 | Difference | GPT-6 Sol | Mistral Medium 3.5 | Difference |
| Invoice extraction | 99.23% | 96.87% | ▼ 2.36 | $10.79 | $4.75 | −56 % |
| Email triage | 98.44% | 94.15% | ▼ 4.29 | $2.77 | $1.79 | −36 % |
| Personal data detection | 99.81% | 99.62% | ▼ 0.19 | $2.21 | $1.41 | −36 % |
| Contract clauses | 100.00% | 100.00% | ±0 | $4.48 | $3.02 | −33 % |
| Document summaries | 97.89% | 100.00% | ▲ 2.11 | $5.02 | $1.86 | −63 % |
| Questions about a document | 100.00% | 100.00% | ±0 | $3.36 | $2.18 | −35 % |
| Accuracy (correct fields) | Per 1,000 documents | |||||
|---|---|---|---|---|---|---|
| Task · documents | GPT-6 Sol | Mistral Medium 3.5 | Difference | GPT-6 Sol | Mistral Medium 3.5 | Difference |
| Invoice extraction | 99.90% | 98.56% | ▼ 1.34 | $11.00 | $4.82 | −56 % |
| Email triage | 98.59% | 94.15% | ▼ 4.44 | $2.81 | $1.78 | −37 % |
| Personal data detection | 99.71% | 99.62% | ▼ 0.09 | $2.23 | $1.43 | −36 % |
| Contract clauses | 99.59% | 100.00% | ▲ 0.41 | $4.49 | $3.01 | −33 % |
| Document summaries | 97.22% | 100.00% | ▲ 2.78 | $4.58 | $1.87 | −59 % |
| Questions about a document | 100.00% | 100.00% | ±0 | $3.43 | $2.19 | −36 % |
Difference: Mistral Medium 3.5 vs. GPT-6 Sol; 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 Sol is more accurate by 2.2 pp. Mistral Medium 3.5 is 2.2× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 99.94% | 97.76% |
| Error-free documents | 99.33% | 79.33% |
| Per 1,000 documents | $9.65 | $4.37 |
| To fix / 1,000 | 7 | 207 |
| Speed (median) | 4.1 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.
Invoice extraction · Czech (150 documents)
GPT-6 Sol is more accurate by 6.4 pp. Mistral Medium 3.5 is 2.2× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 99.90% | 93.49% |
| Error-free documents | 98.67% | 63.33% |
| Per 1,000 documents | $10.12 | $4.69 |
| To fix / 1,000 | 13 | 367 |
| Speed (median) | 3.9 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.
Invoice extraction · German (150 documents)
GPT-6 Sol is more accurate by 2.6 pp. Mistral Medium 3.5 is 2.3× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 99.95% | 97.38% |
| Error-free documents | 99.33% | 74.67% |
| Per 1,000 documents | $10.65 | $4.72 |
| To fix / 1,000 | 7 | 253 |
| Speed (median) | 4.9 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.
Invoice extraction · Spanish (150 documents)
GPT-6 Sol is more accurate by 2.4 pp. Mistral Medium 3.5 is 2.3× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 99.23% | 96.87% |
| Error-free documents | 90.00% | 66.67% |
| Per 1,000 documents | $10.79 | $4.75 |
| To fix / 1,000 | 100 | 333 |
| Speed (median) | 5.9 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.
Invoice extraction · French (150 documents)
GPT-6 Sol is more accurate by 1.3 pp. Mistral Medium 3.5 is 2.3× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 99.90% | 98.56% |
| Error-free documents | 98.67% | 84.67% |
| Per 1,000 documents | $11.00 | $4.82 |
| To fix / 1,000 | 13 | 153 |
| Speed (median) | 6.0 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 · English (US) (150 documents)
GPT-6 Sol is more accurate by 4.1 pp. Mistral Medium 3.5 is 1.7× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 99.04% | 94.89% |
| Error-free documents | 92.00% | 57.33% |
| Per 1,000 documents | $2.44 | $1.47 |
| To fix / 1,000 | 80 | 427 |
| Speed (median) | 2.8 sec | 0.8 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)
GPT-6 Sol is more accurate by 4.4 pp. Mistral Medium 3.5 is 1.6× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 98.96% | 94.52% |
| Error-free documents | 90.67% | 55.33% |
| Per 1,000 documents | $3.19 | $1.95 |
| To fix / 1,000 | 93 | 447 |
| Speed (median) | 2.8 sec | 0.8 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 · German (150 documents)
GPT-6 Sol is more accurate by 5.5 pp. Mistral Medium 3.5 is 1.5× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 98.22% | 92.74% |
| Error-free documents | 84.00% | 48.00% |
| Per 1,000 documents | $2.73 | $1.77 |
| To fix / 1,000 | 160 | 520 |
| Speed (median) | 2.9 sec | 0.8 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)
GPT-6 Sol is more accurate by 4.3 pp. Mistral Medium 3.5 is 1.6× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 98.44% | 94.15% |
| Error-free documents | 86.00% | 54.00% |
| Per 1,000 documents | $2.77 | $1.79 |
| To fix / 1,000 | 140 | 460 |
| Speed (median) | 3.3 sec | 0.9 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 · French (150 documents)
GPT-6 Sol is more accurate by 4.4 pp. Mistral Medium 3.5 is 1.6× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 98.59% | 94.15% |
| Error-free documents | 87.33% | 54.00% |
| Per 1,000 documents | $2.81 | $1.78 |
| To fix / 1,000 | 127 | 460 |
| Speed (median) | 3.2 sec | 0.9 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 · English (US) (150 documents)
Both are equally accurate. Mistral Medium 3.5 is 1.8× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 99.71% | 99.71% |
| Error-free documents | 98.00% | 98.00% |
| Per 1,000 documents | $2.09 | $1.15 |
| To fix / 1,000 | 20 | 20 |
| Speed (median) | 2.6 sec | 0.8 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)
Mistral Medium 3.5 is more accurate by 0.1 pp. Mistral Medium 3.5 is 1.6× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 99.71% | 99.81% |
| Error-free documents | 98.00% | 98.67% |
| Per 1,000 documents | $2.22 | $1.40 |
| To fix / 1,000 | 20 | 13 |
| Speed (median) | 2.5 sec | 0.8 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)
Mistral Medium 3.5 is more accurate by 0.3 pp. Mistral Medium 3.5 is 1.5× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 99.71% | 100.00% |
| Error-free documents | 98.00% | 100.00% |
| Per 1,000 documents | $2.13 | $1.38 |
| To fix / 1,000 | 20 | 0 |
| Speed (median) | 2.6 sec | 0.9 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 · Spanish (150 documents)
GPT-6 Sol is more accurate by 0.2 pp. Mistral Medium 3.5 is 1.6× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 99.81% | 99.62% |
| Error-free documents | 98.67% | 97.33% |
| Per 1,000 documents | $2.21 | $1.41 |
| To fix / 1,000 | 13 | 27 |
| Speed (median) | 2.9 sec | 1.0 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.
Personal data detection · French (150 documents)
GPT-6 Sol is more accurate by 0.1 pp. Mistral Medium 3.5 is 1.6× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 99.71% | 99.62% |
| Error-free documents | 98.00% | 97.33% |
| Per 1,000 documents | $2.23 | $1.43 |
| To fix / 1,000 | 20 | 27 |
| Speed (median) | 2.9 sec | 0.9 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 · English (US) (150 documents)
GPT-6 Sol is more accurate by 1.9 pp. Mistral Medium 3.5 is 1.4× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 100.00% | 98.10% |
| Error-free documents | 100.00% | 87.33% |
| Per 1,000 documents | $3.33 | $2.35 |
| To fix / 1,000 | 0 | 127 |
| Speed (median) | 2.5 sec | 1.1 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 · Czech (150 documents)
Both are equally accurate. Mistral Medium 3.5 is 1.5× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 100.00% | 100.00% |
| Error-free documents | 100.00% | 100.00% |
| Per 1,000 documents | $4.62 | $3.06 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 2.0 sec | 1.2 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 · German (150 documents)
GPT-6 Sol is more accurate by 2.9 pp. Mistral Medium 3.5 is 1.6× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 100.00% | 97.13% |
| Error-free documents | 100.00% | 75.33% |
| Per 1,000 documents | $4.36 | $2.76 |
| To fix / 1,000 | 0 | 247 |
| Speed (median) | 2.9 sec | 1.2 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. Mistral Medium 3.5 is 1.5× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 100.00% | 100.00% |
| Error-free documents | 100.00% | 100.00% |
| Per 1,000 documents | $4.48 | $3.02 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 2.8 sec | 1.3 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.
Contract clauses · French (150 documents)
Mistral Medium 3.5 is more accurate by 0.4 pp. Mistral Medium 3.5 is 1.5× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 99.59% | 100.00% |
| Error-free documents | 94.67% | 100.00% |
| Per 1,000 documents | $4.49 | $3.01 |
| To fix / 1,000 | 53 | 0 |
| Speed (median) | 2.6 sec | 1.3 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 · English (US) (150 documents)
Mistral Medium 3.5 is more accurate by 0.4 pp. Mistral Medium 3.5 is 2.5× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 99.56% | 100.00% |
| Error-free documents | 97.33% | 100.00% |
| Per 1,000 documents | $3.85 | $1.57 |
| To fix / 1,000 | 27 | 0 |
| Speed (median) | 8.1 sec | 0.9 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. Mistral Medium 3.5 is 2× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 100.00% | 100.00% |
| Error-free documents | 100.00% | 100.00% |
| Per 1,000 documents | $4.72 | $2.31 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 7.6 sec | 1.4 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. Mistral Medium 3.5 is 2.1× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 100.00% | 100.00% |
| Error-free documents | 100.00% | 100.00% |
| Per 1,000 documents | $4.11 | $1.98 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 7.1 sec | 1.1 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.
Document summaries · Spanish (150 documents)
Mistral Medium 3.5 is more accurate by 2.1 pp. Mistral Medium 3.5 is 2.7× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 97.89% | 100.00% |
| Error-free documents | 87.33% | 100.00% |
| Per 1,000 documents | $5.02 | $1.86 |
| To fix / 1,000 | 127 | 0 |
| Speed (median) | 7.0 sec | 1.0 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)
Mistral Medium 3.5 is more accurate by 2.8 pp. Mistral Medium 3.5 is 2.5× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 97.22% | 100.00% |
| Error-free documents | 83.33% | 100.00% |
| Per 1,000 documents | $4.58 | $1.87 |
| To fix / 1,000 | 167 | 0 |
| Speed (median) | 6.1 sec | 1.0 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.
Questions about a document · English (US) (150 documents)
Both are equally accurate. Mistral Medium 3.5 is 1.3× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 100.00% | 100.00% |
| Error-free documents | 100.00% | 100.00% |
| Per 1,000 documents | $2.36 | $1.81 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 2.3 sec | 0.8 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.
Questions about a document · Czech (150 documents)
Both are equally accurate. Mistral Medium 3.5 is 1.6× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 100.00% | 100.00% |
| Error-free documents | 100.00% | 100.00% |
| Per 1,000 documents | $3.95 | $2.51 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 2.3 sec | 0.9 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 · German (150 documents)
Both are equally accurate. Mistral Medium 3.5 is 1.5× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 100.00% | 100.00% |
| Error-free documents | 100.00% | 100.00% |
| Per 1,000 documents | $3.23 | $2.13 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 2.2 sec | 0.8 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.
Questions about a document · Spanish (150 documents)
Both are equally accurate. Mistral Medium 3.5 is 1.5× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 100.00% | 100.00% |
| Error-free documents | 100.00% | 100.00% |
| Per 1,000 documents | $3.36 | $2.18 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 2.5 sec | 0.8 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.
Questions about a document · French (150 documents)
Both are equally accurate. Mistral Medium 3.5 is 1.6× cheaper.
| Metric | GPT-6 Sol | Mistral Medium 3.5 |
|---|---|---|
| Correct fields | 100.00% | 100.00% |
| Error-free documents | 100.00% | 100.00% |
| Per 1,000 documents | $3.43 | $2.19 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 2.5 sec | 0.9 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.