JohannesKaufmann/html-to-markdown

⚙️ Convert HTML to Markdown. Even works with entire websites and can be extended through rules.

885

Generated Behavioral Tests

99.9%

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)	99.9%	$61.85	450	trace →
2	Muse Wonder Full	99.3%	TBA	384	trace →
3	GPT 6 Astra (max)	98.6%	$9.66	50	trace →
4	Muse Wonder (xhigh)	98.5%	$37.60	311	trace →
5	Claude Opus 5 (xhigh)	97.5%	$24.08	175	trace →
6	GPT-5.6 Sol (xhigh)	96.2%	$7.23	41	trace →
7	Muse Spark 1.3 (max)	95.6%	$4.85	289	trace →
8	Muse Spark 1.3 (xhigh)	93.6%	$2.32	314	trace →
9	GPT 5.5 (xhigh)	92.8%	$7.12	72	trace →
10	Gemini 3.7 Flash	89.4%	$1.40	114	trace →
11	Gemini 3.5 Flash	88.8%	$4.75	262	trace →
12	GPT 5.5 (high)	88.2%	$2.38	29	trace →
13	Gemini 3.6 Flash	86.2%	$3.86	142	trace →
14	Claude Opus 4.7	85.5%	$3.56	92	trace →
15	Claude Opus 4.8 (xhigh)	84.0%	$13.28	140	trace →
16	GPT-5.6 Sol	83.7%	$1.29	21	trace →
17	Claude Opus 4.6	83.7%	$14.48	363	trace →
18	Claude Sonnet 4.6	81.9%	$18.69	503	trace →
19	Claude Opus 4.7 (xhigh)	81.1%	$10.37	209	trace →
20	GPT 5.5	77.7%	$0.78	15	trace →
21	GPT 5.4	67.2%	$0.23	7	trace →
22	Gemini 3 Flash	65.9%	$0.39	105	trace →
23	GLM-5.2	59.5%	$18.54	187	trace →
24	Claude Haiku 4.5	47.3%	$0.72	111	trace →
25	GPT 5.4 mini	33.2%	$0.05	11	trace →
26	Muse Spark 1.1 (xhigh)	1.5%	$0.49	180	trace →
27	Gemini 3.1 Pro	1.5%	$1.38	113	trace →
28	GPT 5 mini	1.5%	$0.06	31	trace →
29	Claude Fable 5.1 (xhigh)	0.0%	$0.05	5	trace →
30	Muse Spark 1.2 (xhigh)	0.0%	$3.78	376	trace →

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