ModelVerdict

Comparison

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

English (US)
Accuracy (correct fields)Per 1,000 documents
Task · documentsGPT-6 SolMistral Medium 3.5DifferenceGPT-6 SolMistral Medium 3.5Difference
Invoice extraction99.94%97.76%▼ 2.18$9.65$4.37−55 %
Email triage99.04%94.89%▼ 4.15$2.44$1.47−39 %
Personal data detection99.71%99.71%±0$2.09$1.15−45 %
Contract clauses100.00%98.10%▼ 1.9$3.33$2.35−29 %
Document summaries99.56%100.00%▲ 0.44$3.85$1.57−59 %
Questions about a document100.00%100.00%±0$2.36$1.81−23 %
Czech
Accuracy (correct fields)Per 1,000 documents
Task · documentsGPT-6 SolMistral Medium 3.5DifferenceGPT-6 SolMistral Medium 3.5Difference
Invoice extraction99.90%93.49%▼ 6.41$10.12$4.69−54 %
Email triage98.96%94.52%▼ 4.44$3.19$1.95−39 %
Personal data detection99.71%99.81%▲ 0.1$2.22$1.40−37 %
Contract clauses100.00%100.00%±0$4.62$3.06−34 %
Document summaries100.00%100.00%±0$4.72$2.31−51 %
Questions about a document100.00%100.00%±0$3.95$2.51−36 %
German
Accuracy (correct fields)Per 1,000 documents
Task · documentsGPT-6 SolMistral Medium 3.5DifferenceGPT-6 SolMistral Medium 3.5Difference
Invoice extraction99.95%97.38%▼ 2.57$10.65$4.72−56 %
Email triage98.22%92.74%▼ 5.48$2.73$1.77−35 %
Personal data detection99.71%100.00%▲ 0.29$2.13$1.38−35 %
Contract clauses100.00%97.13%▼ 2.87$4.36$2.76−37 %
Document summaries100.00%100.00%±0$4.11$1.98−52 %
Questions about a document100.00%100.00%±0$3.23$2.13−34 %
Spanish
Accuracy (correct fields)Per 1,000 documents
Task · documentsGPT-6 SolMistral Medium 3.5DifferenceGPT-6 SolMistral Medium 3.5Difference
Invoice extraction99.23%96.87%▼ 2.36$10.79$4.75−56 %
Email triage98.44%94.15%▼ 4.29$2.77$1.79−36 %
Personal data detection99.81%99.62%▼ 0.19$2.21$1.41−36 %
Contract clauses100.00%100.00%±0$4.48$3.02−33 %
Document summaries97.89%100.00%▲ 2.11$5.02$1.86−63 %
Questions about a document100.00%100.00%±0$3.36$2.18−35 %
French
Accuracy (correct fields)Per 1,000 documents
Task · documentsGPT-6 SolMistral Medium 3.5DifferenceGPT-6 SolMistral Medium 3.5Difference
Invoice extraction99.90%98.56%▼ 1.34$11.00$4.82−56 %
Email triage98.59%94.15%▼ 4.44$2.81$1.78−37 %
Personal data detection99.71%99.62%▼ 0.09$2.23$1.43−36 %
Contract clauses99.59%100.00%▲ 0.41$4.49$3.01−33 %
Document summaries97.22%100.00%▲ 2.78$4.58$1.87−59 %
Questions about a document100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.94%97.76%
Error-free documents99.33%79.33%
Per 1,000 documents$9.65$4.37
To fix / 1,0007207
Speed (median)4.1 sec2.3 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.90%93.49%
Error-free documents98.67%63.33%
Per 1,000 documents$10.12$4.69
To fix / 1,00013367
Speed (median)3.9 sec2.6 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.95%97.38%
Error-free documents99.33%74.67%
Per 1,000 documents$10.65$4.72
To fix / 1,0007253
Speed (median)4.9 sec2.5 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.23%96.87%
Error-free documents90.00%66.67%
Per 1,000 documents$10.79$4.75
To fix / 1,000100333
Speed (median)5.9 sec2.5 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.90%98.56%
Error-free documents98.67%84.67%
Per 1,000 documents$11.00$4.82
To fix / 1,00013153
Speed (median)6.0 sec2.6 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.04%94.89%
Error-free documents92.00%57.33%
Per 1,000 documents$2.44$1.47
To fix / 1,00080427
Speed (median)2.8 sec0.8 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields98.96%94.52%
Error-free documents90.67%55.33%
Per 1,000 documents$3.19$1.95
To fix / 1,00093447
Speed (median)2.8 sec0.8 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields98.22%92.74%
Error-free documents84.00%48.00%
Per 1,000 documents$2.73$1.77
To fix / 1,000160520
Speed (median)2.9 sec0.8 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields98.44%94.15%
Error-free documents86.00%54.00%
Per 1,000 documents$2.77$1.79
To fix / 1,000140460
Speed (median)3.3 sec0.9 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields98.59%94.15%
Error-free documents87.33%54.00%
Per 1,000 documents$2.81$1.78
To fix / 1,000127460
Speed (median)3.2 sec0.9 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.71%99.71%
Error-free documents98.00%98.00%
Per 1,000 documents$2.09$1.15
To fix / 1,0002020
Speed (median)2.6 sec0.8 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.71%99.81%
Error-free documents98.00%98.67%
Per 1,000 documents$2.22$1.40
To fix / 1,0002013
Speed (median)2.5 sec0.8 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.71%100.00%
Error-free documents98.00%100.00%
Per 1,000 documents$2.13$1.38
To fix / 1,000200
Speed (median)2.6 sec0.9 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.81%99.62%
Error-free documents98.67%97.33%
Per 1,000 documents$2.21$1.41
To fix / 1,0001327
Speed (median)2.9 sec1.0 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.71%99.62%
Error-free documents98.00%97.33%
Per 1,000 documents$2.23$1.43
To fix / 1,0002027
Speed (median)2.9 sec0.9 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields100.00%98.10%
Error-free documents100.00%87.33%
Per 1,000 documents$3.33$2.35
To fix / 1,0000127
Speed (median)2.5 sec1.1 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$4.62$3.06
To fix / 1,00000
Speed (median)2.0 sec1.2 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields100.00%97.13%
Error-free documents100.00%75.33%
Per 1,000 documents$4.36$2.76
To fix / 1,0000247
Speed (median)2.9 sec1.2 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$4.48$3.02
To fix / 1,00000
Speed (median)2.8 sec1.3 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.59%100.00%
Error-free documents94.67%100.00%
Per 1,000 documents$4.49$3.01
To fix / 1,000530
Speed (median)2.6 sec1.3 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields99.56%100.00%
Error-free documents97.33%100.00%
Per 1,000 documents$3.85$1.57
To fix / 1,000270
Speed (median)8.1 sec0.9 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$4.72$2.31
To fix / 1,00000
Speed (median)7.6 sec1.4 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$4.11$1.98
To fix / 1,00000
Speed (median)7.1 sec1.1 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields97.89%100.00%
Error-free documents87.33%100.00%
Per 1,000 documents$5.02$1.86
To fix / 1,0001270
Speed (median)7.0 sec1.0 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields97.22%100.00%
Error-free documents83.33%100.00%
Per 1,000 documents$4.58$1.87
To fix / 1,0001670
Speed (median)6.1 sec1.0 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$2.36$1.81
To fix / 1,00000
Speed (median)2.3 sec0.8 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$3.95$2.51
To fix / 1,00000
Speed (median)2.3 sec0.9 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$3.23$2.13
To fix / 1,00000
Speed (median)2.2 sec0.8 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$3.36$2.18
To fix / 1,00000
Speed (median)2.5 sec0.8 sec
Valid answers100.00%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.

MetricGPT-6 SolMistral Medium 3.5
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$3.43$2.19
To fix / 1,00000
Speed (median)2.5 sec0.9 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Log in with email

We use your email only to log you in (and for the digest if you tick it). No spam.