iframe-proxy | Sunbelt Computer Software

Converts books written in Markdown to HTML, LaTeX/PDF and EPUB

807

Generated Behavioral Tests

85.9%

Best Score

Claude Opus 5 (xhigh)

Results by Model

Hover a point for details · The line marks the Pareto frontier (best score per cost) · Click a point to see model details

21 runs

#	Model	Score	Cost	Calls
1	Claude Opus 5 (xhigh)	85.9%	$118.23	503	trace →
2	Gemini 3.7 Flash	66.5%	$1.77	143	trace →
3	Claude Sonnet 4.6	60.3%	$85.27	937	trace →
4	Claude Opus 4.8 (xhigh)	54.3%	$24.10	188	trace →
5	Gemini 3.5 Flash	50.7%	$7.78	244	trace →
6	GPT 5.5 (high)	48.8%	$3.32	38	trace →
7	GPT-5.6 Sol	46.8%	$1.24	16	trace →
8	Claude Opus 4.6	45.0%	$19.00	320	trace →
9	GPT 5.5	43.2%	$1.04	15	trace →
10	GPT-5.6 Sol (xhigh)	30.1%	$10.67	73	trace →
11	Claude Opus 4.7 (xhigh)	29.4%	$13.25	195	trace →
12	Gemini 3.1 Pro	22.4%	$0.98	81	trace →
13	Claude Haiku 4.5	21.2%	$0.47	106	trace →
14	GPT 5.4	20.6%	$0.34	11	trace →
15	GPT 5 mini	13.6%	$0.04	17	trace →
16	Gemini 3 Flash	12.8%	$0.45	92	trace →
17	GPT 5.4 mini	11.5%	$0.03	9	trace →
18	GPT 5.5 (xhigh)	2.9%	$10.81	98	trace →
19	Gemini 3.6 Flash	2.9%	$4.59	188	trace →
20	GLM-5.2	0.9%	$21.10	230	trace →
21	Claude Opus 4.7	0.9%	$2.01	69	trace →

Click a row to replay how that model rebuilt this program, or the model name to open its full run