ModelVerdict

Comparison

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

English (US)
Accuracy (correct fields)Per 1,000 documents
Task · documentsGemini 3.8 FlashGPT-6 LunaDifferenceGemini 3.8 FlashGPT-6 LunaDifference
Invoice extraction99.82%99.70%▼ 0.12$3.84$0.51−87 %
Email triage98.74%97.48%▼ 1.26$2.39$0.13−94 %
Personal data detection99.71%99.62%▼ 0.09$1.86$0.11−94 %
Contract clauses99.90%99.79%▼ 0.11$2.47$0.20−92 %
Document summaries100.00%100.00%±0$5.46$0.16−97 %
Questions about a document99.89%99.11%▼ 0.78$3.00$0.15−95 %
Czech
Accuracy (correct fields)Per 1,000 documents
Task · documentsGemini 3.8 FlashGPT-6 LunaDifferenceGemini 3.8 FlashGPT-6 LunaDifference
Invoice extraction99.95%99.28%▼ 0.67$4.26$0.51−88 %
Email triage99.19%97.93%▼ 1.26$3.06$0.18−94 %
Personal data detection99.52%99.62%▲ 0.1$2.19$0.12−95 %
Contract clauses100.00%100.00%±0$3.09$0.27−91 %
Document summaries100.00%100.00%±0$6.69$0.21−97 %
Questions about a document100.00%100.00%±0$4.36$0.23−95 %
German
Accuracy (correct fields)Per 1,000 documents
Task · documentsGemini 3.8 FlashGPT-6 LunaDifferenceGemini 3.8 FlashGPT-6 LunaDifference
Invoice extraction97.23%99.23%▲ 2$7.15$0.54−92 %
Email triage98.37%96.96%▼ 1.41$2.74$0.15−94 %
Personal data detection99.71%99.62%▼ 0.09$2.12$0.12−94 %
Contract clauses99.90%100.00%▲ 0.1$3.42$0.27−92 %
Document summaries100.00%100.00%±0$6.11$0.19−97 %
Questions about a document100.00%98.00%▼ 2$3.76$0.20−95 %
Spanish
Accuracy (correct fields)Per 1,000 documents
Task · documentsGemini 3.8 FlashGPT-6 LunaDifferenceGemini 3.8 FlashGPT-6 LunaDifference
Invoice extraction97.28%99.13%▲ 1.85$7.84$0.55−93 %
Email triage98.96%96.81%▼ 2.15$3.30$0.16−95 %
Personal data detection99.81%99.71%▼ 0.1$2.11$0.12−94 %
Contract clauses100.00%100.00%±0$3.33$0.26−92 %
Document summaries100.00%97.00%▼ 3$6.78$0.19−97 %
Questions about a document100.00%99.67%▼ 0.33$4.05$0.19−95 %
French
Accuracy (correct fields)Per 1,000 documents
Task · documentsGemini 3.8 FlashGPT-6 LunaDifferenceGemini 3.8 FlashGPT-6 LunaDifference
Invoice extraction99.95%99.08%▼ 0.87$6.07$0.56−91 %
Email triage98.59%97.26%▼ 1.33$2.63$0.16−94 %
Personal data detection99.81%99.62%▼ 0.19$2.13$0.12−94 %
Contract clauses100.00%99.33%▼ 0.67$3.50$0.27−92 %
Document summaries100.00%98.78%▼ 1.22$7.06$0.20−97 %
Questions about a document100.00%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.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields99.82%99.70%
Error-free documents98.00%96.67%
Per 1,000 documents$3.84$0.51
To fix / 1,0002033
Speed (median)3.2 sec3.4 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.

Invoice extraction · Czech (150 documents)

Gemini 3.8 Flash is more accurate by 0.7 pp. GPT-6 Luna is 8.4× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields99.95%99.28%
Error-free documents99.33%93.33%
Per 1,000 documents$4.26$0.51
To fix / 1,000767
Speed (median)3.5 sec3.2 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.

Invoice extraction · German (150 documents)

GPT-6 Luna is more accurate by 2 pp. GPT-6 Luna is 13.1× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields97.23%99.23%
Error-free documents96.00%91.33%
Per 1,000 documents$7.15$0.54
To fix / 1,0004087
Speed (median)4.7 sec3.7 sec
Valid answers97.33%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.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields97.28%99.13%
Error-free documents96.67%88.67%
Per 1,000 documents$7.84$0.55
To fix / 1,00033113
Speed (median)5.7 sec3.9 sec
Valid answers97.33%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.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields99.95%99.08%
Error-free documents99.33%88.00%
Per 1,000 documents$6.07$0.56
To fix / 1,0007120
Speed (median)5.3 sec3.9 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 · English (US) (150 documents)

Gemini 3.8 Flash is more accurate by 1.3 pp. GPT-6 Luna is 17.7× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields98.74%97.48%
Error-free documents88.67%77.33%
Per 1,000 documents$2.39$0.13
To fix / 1,000113227
Speed (median)2.2 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.

Email triage · Czech (150 documents)

Gemini 3.8 Flash is more accurate by 1.3 pp. GPT-6 Luna is 17.2× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields99.19%97.93%
Error-free documents92.67%81.33%
Per 1,000 documents$3.06$0.18
To fix / 1,00073187
Speed (median)2.6 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 · German (150 documents)

Gemini 3.8 Flash is more accurate by 1.4 pp. GPT-6 Luna is 18× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields98.37%96.96%
Error-free documents85.33%72.67%
Per 1,000 documents$2.74$0.15
To fix / 1,000147273
Speed (median)2.9 sec2.8 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)

Gemini 3.8 Flash is more accurate by 2.2 pp. GPT-6 Luna is 20.9× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields98.96%96.81%
Error-free documents90.67%72.00%
Per 1,000 documents$3.30$0.16
To fix / 1,00093280
Speed (median)3.3 sec3.1 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 · French (150 documents)

Gemini 3.8 Flash is more accurate by 1.3 pp. GPT-6 Luna is 16.4× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields98.59%97.26%
Error-free documents87.33%76.00%
Per 1,000 documents$2.63$0.16
To fix / 1,000127240
Speed (median)2.7 sec2.8 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 · English (US) (150 documents)

Gemini 3.8 Flash is more accurate by 0.1 pp. GPT-6 Luna is 17.6× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields99.71%99.62%
Error-free documents98.00%97.33%
Per 1,000 documents$1.86$0.11
To fix / 1,0002027
Speed (median)1.9 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.

Personal data detection · Czech (150 documents)

GPT-6 Luna is more accurate by 0.1 pp. GPT-6 Luna is 18.3× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields99.52%99.62%
Error-free documents96.67%97.33%
Per 1,000 documents$2.19$0.12
To fix / 1,0003327
Speed (median)2.0 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.

Personal data detection · German (150 documents)

Gemini 3.8 Flash is more accurate by 0.1 pp. GPT-6 Luna is 18.1× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields99.71%99.62%
Error-free documents98.00%97.33%
Per 1,000 documents$2.12$0.12
To fix / 1,0002027
Speed (median)2.3 sec2.2 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.

Personal data detection · Spanish (150 documents)

Gemini 3.8 Flash is more accurate by 0.1 pp. GPT-6 Luna is 17.8× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields99.81%99.71%
Error-free documents98.67%98.00%
Per 1,000 documents$2.11$0.12
To fix / 1,0001320
Speed (median)2.3 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.

Personal data detection · French (150 documents)

Gemini 3.8 Flash is more accurate by 0.2 pp. GPT-6 Luna is 17.2× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields99.81%99.62%
Error-free documents98.67%97.33%
Per 1,000 documents$2.13$0.12
To fix / 1,0001327
Speed (median)2.3 sec2.4 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.

Contract clauses · English (US) (150 documents)

Gemini 3.8 Flash is more accurate by 0.1 pp. GPT-6 Luna is 12.3× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields99.90%99.79%
Error-free documents99.33%98.67%
Per 1,000 documents$2.47$0.20
To fix / 1,000713
Speed (median)2.0 sec2.7 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. GPT-6 Luna is 11.4× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$3.09$0.27
To fix / 1,00000
Speed (median)2.2 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.

Contract clauses · German (150 documents)

GPT-6 Luna is more accurate by 0.1 pp. GPT-6 Luna is 12.8× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields99.90%100.00%
Error-free documents99.33%100.00%
Per 1,000 documents$3.42$0.27
To fix / 1,00070
Speed (median)2.6 sec3.0 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 · Spanish (150 documents)

Both are equally accurate. GPT-6 Luna is 12.6× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$3.33$0.26
To fix / 1,00000
Speed (median)3.0 sec3.1 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 · French (150 documents)

Gemini 3.8 Flash is more accurate by 0.7 pp. GPT-6 Luna is 12.8× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields100.00%99.33%
Error-free documents100.00%91.33%
Per 1,000 documents$3.50$0.27
To fix / 1,000087
Speed (median)3.0 sec3.2 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)

Both are equally accurate. GPT-6 Luna is 34.2× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$5.46$0.16
To fix / 1,00000
Speed (median)5.4 sec2.9 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. GPT-6 Luna is 31.5× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$6.69$0.21
To fix / 1,00000
Speed (median)6.2 sec3.4 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. GPT-6 Luna is 31.5× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$6.11$0.19
To fix / 1,00000
Speed (median)5.8 sec3.3 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)

Gemini 3.8 Flash is more accurate by 3 pp. GPT-6 Luna is 35.9× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields100.00%97.00%
Error-free documents100.00%82.00%
Per 1,000 documents$6.78$0.19
To fix / 1,0000180
Speed (median)5.9 sec3.0 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)

Gemini 3.8 Flash is more accurate by 1.2 pp. GPT-6 Luna is 36× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields100.00%98.78%
Error-free documents100.00%92.67%
Per 1,000 documents$7.06$0.20
To fix / 1,000073
Speed (median)6.7 sec3.2 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.

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.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields99.89%99.11%
Error-free documents99.33%96.00%
Per 1,000 documents$3.00$0.15
To fix / 1,000740
Speed (median)3.0 sec3.1 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.

Questions about a document · Czech (150 documents)

Both are equally accurate. GPT-6 Luna is 19.2× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$4.36$0.23
To fix / 1,00000
Speed (median)3.6 sec3.1 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.

Questions about a document · German (150 documents)

Gemini 3.8 Flash is more accurate by 2 pp. GPT-6 Luna is 18.7× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields100.00%98.00%
Error-free documents100.00%91.33%
Per 1,000 documents$3.76$0.20
To fix / 1,000087
Speed (median)3.2 sec3.2 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.

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.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields100.00%99.67%
Error-free documents100.00%98.67%
Per 1,000 documents$4.05$0.19
To fix / 1,000013
Speed (median)3.6 sec2.9 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 · French (150 documents)

Gemini 3.8 Flash is more accurate by 0.4 pp. GPT-6 Luna is 19.9× cheaper.

MetricGemini 3.8 FlashGPT-6 Luna
Correct fields100.00%99.56%
Error-free documents100.00%98.00%
Per 1,000 documents$4.06$0.20
To fix / 1,000020
Speed (median)3.7 sec3.0 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.

Log in with email

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