mgdm/htmlq | ProgramBench

Like jq, but for HTML.

1,455

Generated Behavioral Tests

100.0%

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)

29 runs

#	Model	Score	Cost	Calls
1	Claude Opus 5.5 (xhigh)	100.0%	$28.25	210	trace →
2	Claude Fable 5.1 (xhigh)	100.0%	$44.61	192	trace →
3	Muse Wonder Full	100.0%	TBA	284	trace →
4	Muse Wonder (xhigh)	99.6%	$27.44	278	trace →
5	Muse Spark 1.3 (max)	99.4%	$4.00	268	trace →
6	Muse Spark 1.3 (xhigh)	98.1%	$1.04	209	trace →
7	GPT 5.5 (xhigh)	98.0%	$5.09	69	trace →
8	GPT-5.6 Sol (xhigh)	97.4%	$2.54	22	trace →
9	GPT 6 Astra (max)	97.0%	$6.33	30	trace →
10	Claude Opus 4.8 (xhigh)	96.6%	$16.43	115	trace →
11	GPT 5.5 (high)	96.4%	$3.62	52	trace →
12	Gemini 3.7 Flash	96.4%	$1.48	134	trace →
13	Claude Opus 4.7 (xhigh)	96.2%	$15.99	192	trace →
14	Gemini 3.5 Flash	95.4%	$5.29	149	trace →
15	GPT-5.6 Sol	95.1%	$0.65	14	trace →
16	Muse Spark 1.2 (xhigh)	94.0%	$1.48	197	trace →
17	Claude Opus 4.6	93.9%	$13.55	325	trace →
18	GLM-5.2	93.8%	$20.51	170	trace →
19	Gemini 3.6 Flash	92.3%	$4.14	213	trace →
20	Claude Opus 4.7	92.3%	$3.11	108	trace →
21	Claude Sonnet 4.6	88.0%	$22.96	627	trace →
22	Gemini 3.1 Pro	87.6%	$1.46	104	trace →
23	Gemini 3 Flash	84.4%	$0.29	140	trace →
24	GPT 5.5	84.3%	$0.99	17	trace →
25	Claude Haiku 4.5	78.0%	$0.58	144	trace →
26	GPT 5.4	60.8%	$0.30	14	trace →
27	GPT 5.4 mini	37.8%	$0.03	9	trace →
28	GPT 5 mini	1.2%	$0.02	13	trace →
29	Claude Opus 5 (xhigh)	0.0%	$4.32	67	trace →

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