ModelVerdict

Comparison

Claude Haiku 5.5 vs GPT-6 Sol

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; Claude Haiku 5.5 is cheaper in 30 of 30 combinations.

More accurate

GPT-6 Sol

wins 18 of 30

Cheaper

Claude Haiku 5.5

cheaper in 30 of 30

Faster

Claude Haiku 5.5

2.1 sec vs 2.9 sec

Fewer fixes

GPT-6 Sol

13 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 SolDifferenceClaude Haiku 5.5GPT-6 SolDifference
Invoice extraction100.00%99.94%▼ 0.06$0.61$9.65+1492 %
Email triage98.15%99.04%▲ 0.89$0.23$2.44+940 %
Personal data detection99.81%99.71%▼ 0.1$0.19$2.09+1014 %
Contract clauses99.69%100.00%▲ 0.31$0.35$3.33+838 %
Document summaries98.33%99.56%▲ 1.23$0.34$3.85+1033 %
Questions about a document100.00%100.00%±0$0.23$2.36+924 %
Czech
Accuracy (correct fields)Per 1,000 documents
Task · documentsClaude Haiku 5.5GPT-6 SolDifferenceClaude Haiku 5.5GPT-6 SolDifference
Invoice extraction99.90%99.90%±0$0.62$10.12+1532 %
Email triage97.63%98.96%▲ 1.33$0.29$3.19+1008 %
Personal data detection99.43%99.71%▲ 0.28$0.21$2.22+957 %
Contract clauses100.00%100.00%±0$0.40$4.62+1058 %
Document summaries95.89%100.00%▲ 4.11$0.32$4.72+1356 %
Questions about a document99.78%100.00%▲ 0.22$0.30$3.95+1207 %
German
Accuracy (correct fields)Per 1,000 documents
Task · documentsClaude Haiku 5.5GPT-6 SolDifferenceClaude Haiku 5.5GPT-6 SolDifference
Invoice extraction99.85%99.95%▲ 0.1$0.71$10.65+1404 %
Email triage97.11%98.22%▲ 1.11$0.32$2.73+752 %
Personal data detection99.62%99.71%▲ 0.09$0.23$2.13+821 %
Contract clauses100.00%100.00%±0$0.48$4.36+798 %
Document summaries99.44%100.00%▲ 0.56$0.46$4.11+788 %
Questions about a document100.00%100.00%±0$0.32$3.23+902 %
Spanish
Accuracy (correct fields)Per 1,000 documents
Task · documentsClaude Haiku 5.5GPT-6 SolDifferenceClaude Haiku 5.5GPT-6 SolDifference
Invoice extraction99.44%99.23%▼ 0.21$0.73$10.79+1376 %
Email triage97.70%98.44%▲ 0.74$0.30$2.77+823 %
Personal data detection100.00%99.81%▼ 0.19$0.23$2.21+865 %
Contract clauses99.95%100.00%▲ 0.05$0.42$4.48+965 %
Document summaries94.11%97.89%▲ 3.78$0.61$5.02+719 %
Questions about a document100.00%100.00%±0$0.29$3.36+1067 %
French
Accuracy (correct fields)Per 1,000 documents
Task · documentsClaude Haiku 5.5GPT-6 SolDifferenceClaude Haiku 5.5GPT-6 SolDifference
Invoice extraction99.85%99.90%▲ 0.05$0.77$11.00+1325 %
Email triage97.41%98.59%▲ 1.18$0.31$2.81+799 %
Personal data detection99.33%99.71%▲ 0.38$0.23$2.23+865 %
Contract clauses99.38%99.59%▲ 0.21$0.45$4.49+891 %
Document summaries92.78%97.22%▲ 4.44$0.66$4.58+590 %
Questions about a document99.22%100.00%▲ 0.78$0.28$3.43+1107 %

Difference: GPT-6 Sol 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 0.1 pp. Claude Haiku 5.5 is 15.9× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields100.00%99.94%
Error-free documents100.00%99.33%
Per 1,000 documents$0.61$9.65
To fix / 1,00007
Speed (median)3.4 sec4.1 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 · Czech (150 documents)

Both are equally accurate. Claude Haiku 5.5 is 16.3× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields99.90%99.90%
Error-free documents98.67%98.67%
Per 1,000 documents$0.62$10.12
To fix / 1,0001313
Speed (median)3.4 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 · German (150 documents)

GPT-6 Sol is more accurate by 0.1 pp. Claude Haiku 5.5 is 15× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields99.85%99.95%
Error-free documents98.00%99.33%
Per 1,000 documents$0.71$10.65
To fix / 1,000207
Speed (median)3.9 sec4.9 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 · Spanish (150 documents)

Claude Haiku 5.5 is more accurate by 0.2 pp. Claude Haiku 5.5 is 14.8× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields99.44%99.23%
Error-free documents92.67%90.00%
Per 1,000 documents$0.73$10.79
To fix / 1,00073100
Speed (median)4.4 sec5.9 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)

Both are equally accurate. Claude Haiku 5.5 is 14.2× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields99.85%99.90%
Error-free documents98.00%98.67%
Per 1,000 documents$0.77$11.00
To fix / 1,0002013
Speed (median)4.6 sec6.0 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.

Email triage · English (US) (150 documents)

GPT-6 Sol is more accurate by 0.9 pp. Claude Haiku 5.5 is 10.4× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields98.15%99.04%
Error-free documents84.00%92.00%
Per 1,000 documents$0.23$2.44
To fix / 1,00016080
Speed (median)1.7 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.

Email triage · Czech (150 documents)

GPT-6 Sol is more accurate by 1.3 pp. Claude Haiku 5.5 is 11.1× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields97.63%98.96%
Error-free documents80.00%90.67%
Per 1,000 documents$0.29$3.19
To fix / 1,00020093
Speed (median)1.9 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 · German (150 documents)

GPT-6 Sol is more accurate by 1.1 pp. Claude Haiku 5.5 is 8.5× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields97.11%98.22%
Error-free documents74.67%84.00%
Per 1,000 documents$0.32$2.73
To fix / 1,000253160
Speed (median)2.1 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.

Email triage · Spanish (150 documents)

GPT-6 Sol is more accurate by 0.7 pp. Claude Haiku 5.5 is 9.2× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields97.70%98.44%
Error-free documents80.00%86.00%
Per 1,000 documents$0.30$2.77
To fix / 1,000200140
Speed (median)2.1 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.

Email triage · French (150 documents)

GPT-6 Sol is more accurate by 1.2 pp. Claude Haiku 5.5 is 9× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields97.41%98.59%
Error-free documents76.67%87.33%
Per 1,000 documents$0.31$2.81
To fix / 1,000233127
Speed (median)2.2 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.

Personal data detection · English (US) (150 documents)

Claude Haiku 5.5 is more accurate by 0.1 pp. Claude Haiku 5.5 is 11.1× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields99.81%99.71%
Error-free documents98.67%98.00%
Per 1,000 documents$0.19$2.09
To fix / 1,0001320
Speed (median)1.7 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.

Personal data detection · Czech (150 documents)

GPT-6 Sol is more accurate by 0.3 pp. Claude Haiku 5.5 is 10.6× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields99.43%99.71%
Error-free documents96.00%98.00%
Per 1,000 documents$0.21$2.22
To fix / 1,0004020
Speed (median)1.8 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.

Personal data detection · German (150 documents)

GPT-6 Sol is more accurate by 0.1 pp. Claude Haiku 5.5 is 9.2× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields99.62%99.71%
Error-free documents97.33%98.00%
Per 1,000 documents$0.23$2.13
To fix / 1,0002720
Speed (median)1.8 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.

Personal data detection · Spanish (150 documents)

Claude Haiku 5.5 is more accurate by 0.2 pp. Claude Haiku 5.5 is 9.7× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields100.00%99.81%
Error-free documents100.00%98.67%
Per 1,000 documents$0.23$2.21
To fix / 1,000013
Speed (median)1.9 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.

Personal data detection · French (150 documents)

GPT-6 Sol is more accurate by 0.4 pp. Claude Haiku 5.5 is 9.6× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields99.33%99.71%
Error-free documents95.33%98.00%
Per 1,000 documents$0.23$2.23
To fix / 1,0004720
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.

Contract clauses · English (US) (150 documents)

GPT-6 Sol is more accurate by 0.3 pp. Claude Haiku 5.5 is 9.4× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields99.69%100.00%
Error-free documents97.33%100.00%
Per 1,000 documents$0.35$3.33
To fix / 1,000270
Speed (median)2.1 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.

Contract clauses · Czech (150 documents)

Both are equally accurate. Claude Haiku 5.5 is 11.6× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$0.40$4.62
To fix / 1,00000
Speed (median)2.4 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.

Contract clauses · German (150 documents)

Both are equally accurate. Claude Haiku 5.5 is 9× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$0.48$4.36
To fix / 1,00000
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.

Contract clauses · Spanish (150 documents)

Both are equally accurate. Claude Haiku 5.5 is 10.6× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields99.95%100.00%
Error-free documents99.33%100.00%
Per 1,000 documents$0.42$4.48
To fix / 1,00070
Speed (median)2.3 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.

Contract clauses · French (150 documents)

GPT-6 Sol is more accurate by 0.2 pp. Claude Haiku 5.5 is 9.9× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields99.38%99.59%
Error-free documents92.00%94.67%
Per 1,000 documents$0.45$4.49
To fix / 1,0008053
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.

Document summaries · English (US) (150 documents)

GPT-6 Sol is more accurate by 1.2 pp. Claude Haiku 5.5 is 11.3× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields98.33%99.56%
Error-free documents90.00%97.33%
Per 1,000 documents$0.34$3.85
To fix / 1,00010027
Speed (median)2.7 sec8.1 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 · Czech (150 documents)

GPT-6 Sol is more accurate by 4.1 pp. Claude Haiku 5.5 is 14.6× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields95.89%100.00%
Error-free documents77.33%100.00%
Per 1,000 documents$0.32$4.72
To fix / 1,0002270
Speed (median)2.1 sec7.6 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 Sol is more accurate by 0.6 pp. Claude Haiku 5.5 is 8.9× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields99.44%100.00%
Error-free documents96.67%100.00%
Per 1,000 documents$0.46$4.11
To fix / 1,000330
Speed (median)3.5 sec7.1 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)

GPT-6 Sol is more accurate by 3.8 pp. Claude Haiku 5.5 is 8.2× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields94.11%97.89%
Error-free documents64.67%87.33%
Per 1,000 documents$0.61$5.02
To fix / 1,000353127
Speed (median)3.8 sec7.0 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 Sol is more accurate by 4.4 pp. Claude Haiku 5.5 is 6.9× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields92.78%97.22%
Error-free documents56.67%83.33%
Per 1,000 documents$0.66$4.58
To fix / 1,000433167
Speed (median)4.0 sec6.1 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 · English (US) (150 documents)

Both are equally accurate. Claude Haiku 5.5 is 10.2× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$0.23$2.36
To fix / 1,00000
Speed (median)1.8 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.

Questions about a document · Czech (150 documents)

GPT-6 Sol is more accurate by 0.2 pp. Claude Haiku 5.5 is 13.1× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields99.78%100.00%
Error-free documents98.67%100.00%
Per 1,000 documents$0.30$3.95
To fix / 1,000130
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.

Questions about a document · German (150 documents)

Both are equally accurate. Claude Haiku 5.5 is 10× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$0.32$3.23
To fix / 1,00000
Speed (median)1.9 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.

Questions about a document · Spanish (150 documents)

Both are equally accurate. Claude Haiku 5.5 is 11.7× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$0.29$3.36
To fix / 1,00000
Speed (median)1.8 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.

Questions about a document · French (150 documents)

GPT-6 Sol is more accurate by 0.8 pp. Claude Haiku 5.5 is 12.1× cheaper.

MetricClaude Haiku 5.5GPT-6 Sol
Correct fields99.22%100.00%
Error-free documents96.67%100.00%
Per 1,000 documents$0.28$3.43
To fix / 1,000330
Speed (median)1.8 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.

Log in with email

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