sibprogrammer/xq | ProgramBench

Command-line XML and HTML beautifier and content extractor

792

Generated Behavioral Tests

96.2%

Best Score

Claude Opus 5.5 (xhigh)

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	Claude Opus 5.5 (xhigh)	96.2%	$40.01	337	trace →
2	Claude Fable 5.1 (xhigh)	95.3%	$54.90	242	trace →
3	Muse Wonder Full	95.1%	TBA	212	trace →
4	GPT 6 Astra (max)	94.4%	$6.98	43	trace →
5	Claude Opus 5 (xhigh)	93.8%	$38.91	253	trace →
6	Muse Spark 1.3 (max)	93.1%	$9.86	431	trace →
7	GPT-5.6 Sol (xhigh)	87.6%	$4.12	26	trace →
8	Gemini 3.7 Flash	87.6%	$2.19	170	trace →
9	Muse Wonder (xhigh)	87.0%	$18.30	257	trace →
10	GPT 5.5 (xhigh)	86.5%	$10.18	99	trace →
11	GLM-5.2	83.4%	$20.91	196	trace →
12	Muse Spark 1.3 (xhigh)	82.2%	$3.27	412	trace →
13	GPT-5.6 Sol	81.8%	$0.77	15	trace →
14	Muse Spark 1.1 (xhigh)	81.6%	$0.08	104	trace →
15	Gemini 3.6 Flash	80.6%	$3.48	169	trace →
16	Claude Opus 4.8 (xhigh)	80.5%	$17.74	119	trace →
17	Claude Opus 4.7 (xhigh)	79.0%	$12.57	214	trace →
18	Muse Spark 1.2 (xhigh)	78.8%	$1.27	217	trace →
19	Claude Opus 4.6	75.9%	$13.82	356	trace →
20	GPT 5.5 (high)	75.8%	$3.52	37	trace →
21	Claude Sonnet 4.6	75.0%	$26.84	625	trace →
22	Gemini 3.5 Flash	73.7%	$5.92	163	trace →
23	GPT 5.5	72.7%	$0.87	16	trace →
24	Gemini 3 Flash	63.5%	$0.31	111	trace →
25	Gemini 3.1 Pro	63.1%	$2.94	158	trace →
26	GPT 5.4	57.8%	$0.66	11	trace →
27	Claude Haiku 4.5	37.8%	$0.98	103	trace →
28	GPT 5.4 mini	37.0%	$0.06	13	trace →
29	Claude Opus 4.7	2.5%	$11.86	227	trace →
30	GPT 5 mini	1.5%	$0.03	15	trace →

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