ModelVerdict

Comparison

Claude Haiku 5.5 vs GPT-6 Luna

Same documents, same prompt: where each model gets it right, what it really costs, and how fast it responds.

Verdict

Claude Haiku 5.5 is more accurate; GPT-6 Luna is cheaper in 30 of 30 combinations.

More accurate

Claude Haiku 5.5

wins 15 of 30

Cheaper

GPT-6 Luna

cheaper in 30 of 30

Faster

Claude Haiku 5.5

2.1 sec vs 3.0 sec

Fewer fixes

Tie

33 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 · documentsClaude Haiku 5.5GPT-6 LunaDifferenceClaude Haiku 5.5GPT-6 LunaDifference
Invoice extraction100.00%99.70%▼ 0.3$0.61$0.51−16 %
Email triage98.15%97.48%▼ 0.67$0.23$0.13−43 %
Personal data detection99.81%99.62%▼ 0.19$0.19$0.11−44 %
Contract clauses99.69%99.79%▲ 0.1$0.35$0.20−43 %
Document summaries98.33%100.00%▲ 1.67$0.34$0.16−53 %
Questions about a document100.00%99.11%▼ 0.89$0.23$0.15−34 %
Czech
Accuracy (correct fields)Per 1,000 documents
Task · documentsClaude Haiku 5.5GPT-6 LunaDifferenceClaude Haiku 5.5GPT-6 LunaDifference
Invoice extraction99.90%99.28%▼ 0.62$0.62$0.51−19 %
Email triage97.63%97.93%▲ 0.3$0.29$0.18−38 %
Personal data detection99.43%99.62%▲ 0.19$0.21$0.12−43 %
Contract clauses100.00%100.00%±0$0.40$0.27−32 %
Document summaries95.89%100.00%▲ 4.11$0.32$0.21−35 %
Questions about a document99.78%100.00%▲ 0.22$0.30$0.23−25 %
German
Accuracy (correct fields)Per 1,000 documents
Task · documentsClaude Haiku 5.5GPT-6 LunaDifferenceClaude Haiku 5.5GPT-6 LunaDifference
Invoice extraction99.85%99.23%▼ 0.62$0.71$0.54−23 %
Email triage97.11%96.96%▼ 0.15$0.32$0.15−52 %
Personal data detection99.62%99.62%±0$0.23$0.12−49 %
Contract clauses100.00%100.00%±0$0.48$0.27−45 %
Document summaries99.44%100.00%▲ 0.56$0.46$0.19−58 %
Questions about a document100.00%98.00%▼ 2$0.32$0.20−38 %
Spanish
Accuracy (correct fields)Per 1,000 documents
Task · documentsClaude Haiku 5.5GPT-6 LunaDifferenceClaude Haiku 5.5GPT-6 LunaDifference
Invoice extraction99.44%99.13%▼ 0.31$0.73$0.55−24 %
Email triage97.70%96.81%▼ 0.89$0.30$0.16−47 %
Personal data detection100.00%99.71%▼ 0.29$0.23$0.12−48 %
Contract clauses99.95%100.00%▲ 0.05$0.42$0.26−37 %
Document summaries94.11%97.00%▲ 2.89$0.61$0.19−69 %
Questions about a document100.00%99.67%▼ 0.33$0.29$0.19−32 %
French
Accuracy (correct fields)Per 1,000 documents
Task · documentsClaude Haiku 5.5GPT-6 LunaDifferenceClaude Haiku 5.5GPT-6 LunaDifference
Invoice extraction99.85%99.08%▼ 0.77$0.77$0.56−28 %
Email triage97.41%97.26%▼ 0.15$0.31$0.16−49 %
Personal data detection99.33%99.62%▲ 0.29$0.23$0.12−46 %
Contract clauses99.38%99.33%▼ 0.05$0.45$0.27−40 %
Document summaries92.78%98.78%▲ 6$0.66$0.20−70 %
Questions about a document99.22%99.56%▲ 0.34$0.28$0.20−28 %

Difference: GPT-6 Luna vs. Claude Haiku 5.5; 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)

Claude Haiku 5.5 is more accurate by 0.3 pp. GPT-6 Luna is 1.2× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields100.00%99.70%
Error-free documents100.00%96.67%
Per 1,000 documents$0.61$0.51
To fix / 1,000033
Speed (median)3.4 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)

Claude Haiku 5.5 is more accurate by 0.6 pp. GPT-6 Luna is 1.2× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields99.90%99.28%
Error-free documents98.67%93.33%
Per 1,000 documents$0.62$0.51
To fix / 1,0001367
Speed (median)3.4 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)

Claude Haiku 5.5 is more accurate by 0.6 pp. GPT-6 Luna is 1.3× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields99.85%99.23%
Error-free documents98.00%91.33%
Per 1,000 documents$0.71$0.54
To fix / 1,0002087
Speed (median)3.9 sec3.7 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.

Invoice extraction · Spanish (150 documents)

Claude Haiku 5.5 is more accurate by 0.3 pp. GPT-6 Luna is 1.3× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields99.44%99.13%
Error-free documents92.67%88.67%
Per 1,000 documents$0.73$0.55
To fix / 1,00073113
Speed (median)4.4 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.

Invoice extraction · French (150 documents)

Claude Haiku 5.5 is more accurate by 0.8 pp. GPT-6 Luna is 1.4× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields99.85%99.08%
Error-free documents98.00%88.00%
Per 1,000 documents$0.77$0.56
To fix / 1,00020120
Speed (median)4.6 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)

Claude Haiku 5.5 is more accurate by 0.7 pp. GPT-6 Luna is 1.7× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields98.15%97.48%
Error-free documents84.00%77.33%
Per 1,000 documents$0.23$0.13
To fix / 1,000160227
Speed (median)1.7 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)

GPT-6 Luna is more accurate by 0.3 pp. GPT-6 Luna is 1.6× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields97.63%97.93%
Error-free documents80.00%81.33%
Per 1,000 documents$0.29$0.18
To fix / 1,000200187
Speed (median)1.9 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.

Email triage · German (150 documents)

Claude Haiku 5.5 is more accurate by 0.1 pp. GPT-6 Luna is 2.1× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields97.11%96.96%
Error-free documents74.67%72.67%
Per 1,000 documents$0.32$0.15
To fix / 1,000253273
Speed (median)2.1 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)

Claude Haiku 5.5 is more accurate by 0.9 pp. GPT-6 Luna is 1.9× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields97.70%96.81%
Error-free documents80.00%72.00%
Per 1,000 documents$0.30$0.16
To fix / 1,000200280
Speed (median)2.1 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)

Claude Haiku 5.5 is more accurate by 0.1 pp. GPT-6 Luna is 2× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields97.41%97.26%
Error-free documents76.67%76.00%
Per 1,000 documents$0.31$0.16
To fix / 1,000233240
Speed (median)2.2 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)

Claude Haiku 5.5 is more accurate by 0.2 pp. GPT-6 Luna is 1.8× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields99.81%99.62%
Error-free documents98.67%97.33%
Per 1,000 documents$0.19$0.11
To fix / 1,0001327
Speed (median)1.7 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 0.2 pp. GPT-6 Luna is 1.8× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields99.43%99.62%
Error-free documents96.00%97.33%
Per 1,000 documents$0.21$0.12
To fix / 1,0004027
Speed (median)1.8 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)

Both are equally accurate. GPT-6 Luna is 2× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields99.62%99.62%
Error-free documents97.33%97.33%
Per 1,000 documents$0.23$0.12
To fix / 1,0002727
Speed (median)1.8 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)

Claude Haiku 5.5 is more accurate by 0.3 pp. GPT-6 Luna is 1.9× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields100.00%99.71%
Error-free documents100.00%98.00%
Per 1,000 documents$0.23$0.12
To fix / 1,000020
Speed (median)1.9 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)

GPT-6 Luna is more accurate by 0.3 pp. GPT-6 Luna is 1.9× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields99.33%99.62%
Error-free documents95.33%97.33%
Per 1,000 documents$0.23$0.12
To fix / 1,0004727
Speed (median)1.8 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)

GPT-6 Luna is more accurate by 0.1 pp. GPT-6 Luna is 1.8× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields99.69%99.79%
Error-free documents97.33%98.67%
Per 1,000 documents$0.35$0.20
To fix / 1,0002713
Speed (median)2.1 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 1.5× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$0.40$0.27
To fix / 1,00000
Speed (median)2.4 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)

Both are equally accurate. GPT-6 Luna is 1.8× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$0.48$0.27
To fix / 1,00000
Speed (median)2.7 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.

Contract clauses · Spanish (150 documents)

Both are equally accurate. GPT-6 Luna is 1.6× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields99.95%100.00%
Error-free documents99.33%100.00%
Per 1,000 documents$0.42$0.26
To fix / 1,00070
Speed (median)2.3 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.

Contract clauses · French (150 documents)

Claude Haiku 5.5 is more accurate by 0.1 pp. GPT-6 Luna is 1.7× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields99.38%99.33%
Error-free documents92.00%91.33%
Per 1,000 documents$0.45$0.27
To fix / 1,0008087
Speed (median)2.6 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)

GPT-6 Luna is more accurate by 1.7 pp. GPT-6 Luna is 2.1× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields98.33%100.00%
Error-free documents90.00%100.00%
Per 1,000 documents$0.34$0.16
To fix / 1,0001000
Speed (median)2.7 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)

GPT-6 Luna is more accurate by 4.1 pp. GPT-6 Luna is 1.5× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields95.89%100.00%
Error-free documents77.33%100.00%
Per 1,000 documents$0.32$0.21
To fix / 1,0002270
Speed (median)2.1 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)

GPT-6 Luna is more accurate by 0.6 pp. GPT-6 Luna is 2.4× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields99.44%100.00%
Error-free documents96.67%100.00%
Per 1,000 documents$0.46$0.19
To fix / 1,000330
Speed (median)3.5 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)

GPT-6 Luna is more accurate by 2.9 pp. GPT-6 Luna is 3.3× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields94.11%97.00%
Error-free documents64.67%82.00%
Per 1,000 documents$0.61$0.19
To fix / 1,000353180
Speed (median)3.8 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)

GPT-6 Luna is more accurate by 6 pp. GPT-6 Luna is 3.4× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields92.78%98.78%
Error-free documents56.67%92.67%
Per 1,000 documents$0.66$0.20
To fix / 1,00043373
Speed (median)4.0 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.

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

Claude Haiku 5.5 is more accurate by 0.9 pp. GPT-6 Luna is 1.5× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields100.00%99.11%
Error-free documents100.00%96.00%
Per 1,000 documents$0.23$0.15
To fix / 1,000040
Speed (median)1.8 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)

GPT-6 Luna is more accurate by 0.2 pp. GPT-6 Luna is 1.3× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields99.78%100.00%
Error-free documents98.67%100.00%
Per 1,000 documents$0.30$0.23
To fix / 1,000130
Speed (median)1.9 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)

Claude Haiku 5.5 is more accurate by 2 pp. GPT-6 Luna is 1.6× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields100.00%98.00%
Error-free documents100.00%91.33%
Per 1,000 documents$0.32$0.20
To fix / 1,000087
Speed (median)1.9 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)

Claude Haiku 5.5 is more accurate by 0.3 pp. GPT-6 Luna is 1.5× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields100.00%99.67%
Error-free documents100.00%98.67%
Per 1,000 documents$0.29$0.19
To fix / 1,000013
Speed (median)1.8 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)

GPT-6 Luna is more accurate by 0.3 pp. GPT-6 Luna is 1.4× cheaper.

MetricClaude Haiku 5.5GPT-6 Luna
Correct fields99.22%99.56%
Error-free documents96.67%98.00%
Per 1,000 documents$0.28$0.20
To fix / 1,0003320
Speed (median)1.8 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.