parcel-bundler/lightningcss

An extremely fast CSS parser, transformer, bundler, and minifier written in Rust.

2,828

Generated Behavioral Tests

85.5%

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)	85.5%	$42.91	289	trace →
2	Muse Wonder Full	78.7%	TBA	336	trace →
3	GPT 6 Astra (max)	77.7%	$18.02	86	trace →
4	Claude Fable 5.1 (xhigh)	75.2%	$105.58	256	trace →
5	Muse Wonder (xhigh)	73.0%	$29.05	243	trace →
6	GPT-5.6 Sol (xhigh)	63.1%	$12.01	80	trace →
7	Claude Opus 5 (xhigh)	60.3%	$15.28	137	trace →
8	Muse Spark 1.3 (xhigh)	58.2%	$1.91	248	trace →
9	GPT 5.5 (xhigh)	55.0%	$8.05	68	trace →
10	Claude Opus 4.6	53.6%	$17.40	312	trace →
11	GPT 5.5 (high)	52.7%	$3.53	40	trace →
12	Gemini 3.7 Flash	52.2%	$0.99	100	trace →
13	Claude Sonnet 4.6	49.9%	$45.82	705	trace →
14	GLM-5.2	49.8%	$21.12	247	trace →
15	Gemini 3.5 Flash	49.7%	$6.09	211	trace →
16	Muse Spark 1.2 (xhigh)	48.7%	$1.06	128	trace →
17	Muse Spark 1.1 (xhigh)	48.1%	$0.45	197	trace →
18	Claude Opus 4.7 (xhigh)	46.5%	$4.45	107	trace →
19	GPT-5.6 Sol	45.0%	$1.33	17	trace →
20	GPT 5.5	44.9%	$1.23	20	trace →
21	Claude Opus 4.7	43.2%	$1.26	46	trace →
22	Gemini 3 Flash	43.0%	$0.33	117	trace →
23	Gemini 3.6 Flash	38.4%	$3.18	147	trace →
24	GPT 5.4	36.7%	$0.25	12	trace →
25	GPT 5 mini	36.6%	$0.03	23	trace →
26	Gemini 3.1 Pro	34.0%	$1.22	91	trace →
27	GPT 5.4 mini	31.8%	$0.03	22	trace →
28	Claude Haiku 4.5	28.7%	$1.29	165	trace →
29	Claude Opus 4.8 (xhigh)	0.7%	$18.78	118	trace →
30	Muse Spark 1.3 (max)	0.0%	$10.15	440	trace →

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