crowdagger/crowbook | ProgramBench

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

807

Generated Behavioral Tests

95.4%

Best Score

Muse Wonder Full

Results by Model

Hover for details · Click a model to open it · Drag to zoom the x-axis · Shift-drag to pan · The line marks the Pareto frontier (best score per cost)

30 runs

#	Model	Score	Cost	Calls
1	Muse Wonder Full	95.4%	TBA	479	trace →
2	GPT 6 Astra (max)	93.1%	$13.39	75	trace →
3	Muse Wonder (xhigh)	92.7%	$42.89	383	trace →
4	Claude Opus 5.5 (xhigh)	92.4%	$61.97	428	trace →
5	Claude Fable 5.1 (xhigh)	87.9%	$101.91	404	trace →
6	Claude Opus 5 (xhigh)	85.9%	$118.23	503	trace →
7	Muse Spark 1.3 (xhigh)	67.2%	$1.90	308	trace →
8	Gemini 3.7 Flash	66.5%	$1.77	143	trace →
9	Claude Sonnet 4.6	60.3%	$85.27	937	trace →
10	Claude Opus 4.8 (xhigh)	54.3%	$24.10	188	trace →
11	Gemini 3.5 Flash	50.7%	$7.78	244	trace →
12	GPT 5.5 (high)	48.8%	$3.32	38	trace →
13	GPT-5.6 Sol	46.8%	$1.24	16	trace →
14	Claude Opus 4.6	45.0%	$19.00	320	trace →
15	Muse Spark 1.2 (xhigh)	44.4%	$0.42	98	trace →
16	GPT 5.5	43.2%	$1.04	15	trace →
17	Muse Spark 1.1 (xhigh)	40.0%	$0.62	243	trace →
18	GPT-5.6 Sol (xhigh)	30.1%	$10.67	73	trace →
19	Claude Opus 4.7 (xhigh)	29.4%	$13.25	195	trace →
20	Gemini 3.1 Pro	22.4%	$0.98	81	trace →
21	Claude Haiku 4.5	21.2%	$0.47	106	trace →
22	GPT 5.4	20.6%	$0.34	11	trace →
23	GPT 5 mini	13.6%	$0.04	17	trace →
24	Gemini 3 Flash	12.8%	$0.45	92	trace →
25	GPT 5.4 mini	11.5%	$0.03	9	trace →
26	GPT 5.5 (xhigh)	2.9%	$10.81	98	trace →
27	Gemini 3.6 Flash	2.9%	$4.59	188	trace →
28	GLM-5.2	0.9%	$21.10	230	trace →
29	Claude Opus 4.7	0.9%	$2.01	69	trace →
30	Muse Spark 1.3 (max)	0.0%	$7.00	291	trace →

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