ModelVerdict

Comparison

GPT-6 Luna vs Mistral Small 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; Mistral Small 4 is cheaper in 25 of 30 combinations.

More accurate

GPT-6 Luna

wins 23 of 30

Cheaper

Mistral Small 4

cheaper in 25 of 30

Faster

Mistral Small 4

1.0 sec vs 3.0 sec

Fewer fixes

GPT-6 Luna

33 vs 100 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 LunaMistral Small 4DifferenceGPT-6 LunaMistral Small 4Difference
Invoice extraction99.70%95.58%▼ 4.12$0.51$0.41−20 %
Email triage97.48%89.70%▼ 7.78$0.13$0.09−30 %
Personal data detection99.62%99.43%▼ 0.19$0.11$0.08−27 %
Contract clauses99.79%91.54%▼ 8.25$0.20$0.17−15 %
Document summaries100.00%99.67%▼ 0.33$0.16$0.14−11 %
Questions about a document99.11%100.00%▲ 0.89$0.15$0.15±0 %
Czech
Accuracy (correct fields)Per 1,000 documents
Task · documentsGPT-6 LunaMistral Small 4DifferenceGPT-6 LunaMistral Small 4Difference
Invoice extraction99.28%93.64%▼ 5.64$0.51$0.44−13 %
Email triage97.93%87.63%▼ 10.3$0.18$0.12−34 %
Personal data detection99.62%98.76%▼ 0.86$0.12$0.09−22 %
Contract clauses100.00%99.03%▼ 0.97$0.27$0.23−16 %
Document summaries100.00%99.00%▼ 1$0.21$0.22+4 %
Questions about a document100.00%100.00%±0$0.23$0.21−5 %
German
Accuracy (correct fields)Per 1,000 documents
Task · documentsGPT-6 LunaMistral Small 4DifferenceGPT-6 LunaMistral Small 4Difference
Invoice extraction99.23%94.82%▼ 4.41$0.54$0.44−20 %
Email triage96.96%87.26%▼ 9.7$0.15$0.11−28 %
Personal data detection99.62%99.14%▼ 0.48$0.12$0.09−22 %
Contract clauses100.00%94.26%▼ 5.74$0.27$0.21−22 %
Document summaries100.00%99.89%▼ 0.11$0.19$0.19−3 %
Questions about a document98.00%100.00%▲ 2$0.20$0.18−12 %
Spanish
Accuracy (correct fields)Per 1,000 documents
Task · documentsGPT-6 LunaMistral Small 4DifferenceGPT-6 LunaMistral Small 4Difference
Invoice extraction99.13%92.36%▼ 6.77$0.55$0.44−20 %
Email triage96.81%88.67%▼ 8.14$0.16$0.11−30 %
Personal data detection99.71%99.05%▼ 0.66$0.12$0.09−21 %
Contract clauses100.00%100.00%±0$0.26$0.23−12 %
Document summaries97.00%97.78%▲ 0.78$0.19$0.18−3 %
Questions about a document99.67%100.00%▲ 0.33$0.19$0.18−6 %
French
Accuracy (correct fields)Per 1,000 documents
Task · documentsGPT-6 LunaMistral Small 4DifferenceGPT-6 LunaMistral Small 4Difference
Invoice extraction99.08%94.87%▼ 4.21$0.56$0.44−20 %
Email triage97.26%90.52%▼ 6.74$0.16$0.11−29 %
Personal data detection99.62%98.95%▼ 0.67$0.12$0.09−24 %
Contract clauses99.33%99.23%▼ 0.1$0.27$0.23−15 %
Document summaries98.78%93.22%▼ 5.56$0.20$0.19−3 %
Questions about a document99.56%100.00%▲ 0.44$0.20$0.18−11 %

Difference: Mistral Small 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 4.1 pp. Mistral Small 4 is 1.2× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields99.70%95.58%
Error-free documents96.67%58.00%
Per 1,000 documents$0.51$0.41
To fix / 1,00033420
Speed (median)3.4 sec1.8 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.

Invoice extraction · Czech (150 documents)

GPT-6 Luna is more accurate by 5.6 pp. Mistral Small 4 is 1.2× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields99.28%93.64%
Error-free documents93.33%56.00%
Per 1,000 documents$0.51$0.44
To fix / 1,00067440
Speed (median)3.2 sec2.0 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.

Invoice extraction · German (150 documents)

GPT-6 Luna is more accurate by 4.4 pp. Mistral Small 4 is 1.2× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields99.23%94.82%
Error-free documents91.33%51.33%
Per 1,000 documents$0.54$0.44
To fix / 1,00087487
Speed (median)3.7 sec2.0 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.

Invoice extraction · Spanish (150 documents)

GPT-6 Luna is more accurate by 6.8 pp. Mistral Small 4 is 1.2× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields99.13%92.36%
Error-free documents88.67%32.67%
Per 1,000 documents$0.55$0.44
To fix / 1,000113673
Speed (median)3.9 sec2.1 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.

Invoice extraction · French (150 documents)

GPT-6 Luna is more accurate by 4.2 pp. Mistral Small 4 is 1.3× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields99.08%94.87%
Error-free documents88.00%52.67%
Per 1,000 documents$0.56$0.44
To fix / 1,000120473
Speed (median)3.9 sec2.1 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.

Email triage · English (US) (150 documents)

GPT-6 Luna is more accurate by 7.8 pp. Mistral Small 4 is 1.4× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields97.48%89.70%
Error-free documents77.33%37.33%
Per 1,000 documents$0.13$0.09
To fix / 1,000227627
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.

Email triage · Czech (150 documents)

GPT-6 Luna is more accurate by 10.3 pp. Mistral Small 4 is 1.5× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields97.93%87.63%
Error-free documents81.33%31.33%
Per 1,000 documents$0.18$0.12
To fix / 1,000187687
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.

Email triage · German (150 documents)

GPT-6 Luna is more accurate by 9.7 pp. Mistral Small 4 is 1.4× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields96.96%87.26%
Error-free documents72.67%29.33%
Per 1,000 documents$0.15$0.11
To fix / 1,000273707
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 · Spanish (150 documents)

GPT-6 Luna is more accurate by 8.1 pp. Mistral Small 4 is 1.4× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields96.81%88.67%
Error-free documents72.00%35.33%
Per 1,000 documents$0.16$0.11
To fix / 1,000280647
Speed (median)3.1 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.

Email triage · French (150 documents)

GPT-6 Luna is more accurate by 6.7 pp. Mistral Small 4 is 1.4× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields97.26%90.52%
Error-free documents76.00%44.67%
Per 1,000 documents$0.16$0.11
To fix / 1,000240553
Speed (median)2.8 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)

GPT-6 Luna is more accurate by 0.2 pp. Mistral Small 4 is 1.4× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields99.62%99.43%
Error-free documents97.33%96.00%
Per 1,000 documents$0.11$0.08
To fix / 1,0002740
Speed (median)1.8 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.

Personal data detection · Czech (150 documents)

GPT-6 Luna is more accurate by 0.9 pp. Mistral Small 4 is 1.3× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields99.62%98.76%
Error-free documents97.33%92.00%
Per 1,000 documents$0.12$0.09
To fix / 1,0002780
Speed (median)1.8 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 · German (150 documents)

GPT-6 Luna is more accurate by 0.5 pp. Mistral Small 4 is 1.3× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields99.62%99.14%
Error-free documents97.33%94.00%
Per 1,000 documents$0.12$0.09
To fix / 1,0002760
Speed (median)2.2 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 · Spanish (150 documents)

GPT-6 Luna is more accurate by 0.7 pp. Mistral Small 4 is 1.3× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields99.71%99.05%
Error-free documents98.00%93.33%
Per 1,000 documents$0.12$0.09
To fix / 1,0002067
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.

Personal data detection · French (150 documents)

GPT-6 Luna is more accurate by 0.7 pp. Mistral Small 4 is 1.3× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields99.62%98.95%
Error-free documents97.33%93.33%
Per 1,000 documents$0.12$0.09
To fix / 1,0002767
Speed (median)2.4 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.

Contract clauses · English (US) (150 documents)

GPT-6 Luna is more accurate by 8.3 pp. Mistral Small 4 is 1.2× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields99.79%91.54%
Error-free documents98.67%43.33%
Per 1,000 documents$0.20$0.17
To fix / 1,00013567
Speed (median)2.7 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)

GPT-6 Luna is more accurate by 1 pp. Mistral Small 4 is 1.2× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields100.00%99.03%
Error-free documents100.00%92.00%
Per 1,000 documents$0.27$0.23
To fix / 1,000080
Speed (median)2.6 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 Luna is more accurate by 5.7 pp. Mistral Small 4 is 1.3× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields100.00%94.26%
Error-free documents100.00%46.67%
Per 1,000 documents$0.27$0.21
To fix / 1,0000533
Speed (median)3.0 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 · Spanish (150 documents)

Both are equally accurate. Mistral Small 4 is 1.1× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$0.26$0.23
To fix / 1,00000
Speed (median)3.1 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)

GPT-6 Luna is more accurate by 0.1 pp. Mistral Small 4 is 1.2× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields99.33%99.23%
Error-free documents91.33%90.00%
Per 1,000 documents$0.27$0.23
To fix / 1,00087100
Speed (median)3.2 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.

Document summaries · English (US) (150 documents)

GPT-6 Luna is more accurate by 0.3 pp. Mistral Small 4 is 1.1× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields100.00%99.67%
Error-free documents100.00%98.67%
Per 1,000 documents$0.16$0.14
To fix / 1,000013
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.

Document summaries · Czech (150 documents)

GPT-6 Luna is more accurate by 1 pp.

MetricGPT-6 LunaMistral Small 4
Correct fields100.00%99.00%
Error-free documents100.00%94.00%
Per 1,000 documents$0.21$0.22
To fix / 1,000060
Speed (median)3.4 sec1.6 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.

Document summaries · German (150 documents)

GPT-6 Luna is more accurate by 0.1 pp.

MetricGPT-6 LunaMistral Small 4
Correct fields100.00%99.89%
Error-free documents100.00%99.33%
Per 1,000 documents$0.19$0.19
To fix / 1,00007
Speed (median)3.3 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 · Spanish (150 documents)

Mistral Small 4 is more accurate by 0.8 pp.

MetricGPT-6 LunaMistral Small 4
Correct fields97.00%97.78%
Error-free documents82.00%86.67%
Per 1,000 documents$0.19$0.18
To fix / 1,000180133
Speed (median)3.0 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.

Document summaries · French (150 documents)

GPT-6 Luna is more accurate by 5.6 pp.

MetricGPT-6 LunaMistral Small 4
Correct fields98.78%93.22%
Error-free documents92.67%62.00%
Per 1,000 documents$0.20$0.19
To fix / 1,00073380
Speed (median)3.2 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.

Questions about a document · English (US) (150 documents)

Mistral Small 4 is more accurate by 0.9 pp.

MetricGPT-6 LunaMistral Small 4
Correct fields99.11%100.00%
Error-free documents96.00%100.00%
Per 1,000 documents$0.15$0.15
To fix / 1,000400
Speed (median)3.1 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 Small 4 is 1.1× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$0.23$0.21
To fix / 1,00000
Speed (median)3.1 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 · German (150 documents)

Mistral Small 4 is more accurate by 2 pp. Mistral Small 4 is 1.1× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields98.00%100.00%
Error-free documents91.33%100.00%
Per 1,000 documents$0.20$0.18
To fix / 1,000870
Speed (median)3.2 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)

Mistral Small 4 is more accurate by 0.3 pp. Mistral Small 4 is 1.1× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields99.67%100.00%
Error-free documents98.67%100.00%
Per 1,000 documents$0.19$0.18
To fix / 1,000130
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.

Questions about a document · French (150 documents)

Mistral Small 4 is more accurate by 0.4 pp. Mistral Small 4 is 1.1× cheaper.

MetricGPT-6 LunaMistral Small 4
Correct fields99.56%100.00%
Error-free documents98.00%100.00%
Per 1,000 documents$0.20$0.18
To fix / 1,000200
Speed (median)3.0 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.

Log in with email

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