svenstaro/miniserve | ProgramBench

🌟 For when you really just want to serve some files over HTTP right now!

304

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)

30 runs

#	Model	Score	Cost	Calls
1	Claude Opus 5.5 (xhigh)	100.0%	$41.76	298	trace →
2	Claude Fable 5.1 (xhigh)	99.7%	$83.37	311	trace →
3	Muse Wonder Full	99.7%	TBA	388	trace →
4	GPT 6 Astra (max)	99.0%	$13.35	61	trace →
5	Muse Wonder (xhigh)	98.4%	$19.31	247	trace →
6	Claude Opus 5 (xhigh)	98.0%	$95.37	426	trace →
7	Claude Opus 4.8 (xhigh)	94.2%	$44.46	251	trace →
8	Muse Spark 1.1 (xhigh)	93.1%	$0.69	135	trace →
9	GPT 5.5 (xhigh)	92.4%	$8.11	57	trace →
10	Gemini 3.7 Flash	88.5%	$1.44	120	trace →
11	GPT 5.5 (high)	88.2%	$3.94	31	trace →
12	Muse Spark 1.3 (xhigh)	85.9%	$0.94	178	trace →
13	GPT-5.6 Sol	85.5%	$1.04	15	trace →
14	GPT-5.6 Sol (xhigh)	85.2%	$6.80	41	trace →
15	Muse Spark 1.3 (max)	84.5%	$8.10	335	trace →
16	Gemini 3.5 Flash	82.6%	$5.74	153	trace →
17	GPT 5.5	80.3%	$1.24	16	trace →
18	Claude Opus 4.6	78.6%	$9.68	137	trace →
19	Muse Spark 1.2 (xhigh)	77.3%	$5.44	222	trace →
20	Claude Opus 4.7 (xhigh)	77.0%	$2.94	68	trace →
21	Claude Sonnet 4.6	76.0%	$25.03	420	trace →
22	GLM-5.2	63.9%	$12.95	173	trace →
23	Gemini 3.1 Pro	59.5%	$0.76	41	trace →
24	Claude Opus 4.7	59.2%	$0.94	30	trace →
25	GPT 5.4	58.6%	$0.23	8	trace →
26	Claude Haiku 4.5	45.4%	$0.62	107	trace →
27	Gemini 3 Flash	39.8%	$0.30	63	trace →
28	GPT 5.4 mini	14.8%	$0.05	26	trace →
29	Gemini 3.6 Flash	9.9%	$6.99	154	trace →
30	GPT 5 mini	9.5%	$0.03	13	trace →

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