sstadick/hck | ProgramBench

A sharp cut(1) clone.

855

Generated Behavioral Tests

100.0%

Best Score

Claude Fable 5.1 (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 Fable 5.1 (xhigh)	100.0%	$93.16	277	trace →
2	Muse Wonder Full	99.5%	TBA	201	trace →
3	GPT 6 Astra (max)	99.5%	$14.62	56	trace →
4	Claude Opus 5.5 (xhigh)	99.4%	$34.63	273	trace →
5	Claude Opus 5 (xhigh)	99.1%	$65.89	332	trace →
6	Muse Wonder (xhigh)	98.9%	$18.34	225	trace →
7	Muse Spark 1.3 (max)	98.9%	$2.50	183	trace →
8	Muse Spark 1.3 (xhigh)	98.0%	$1.19	194	trace →
9	GPT 5.5 (xhigh)	97.2%	$7.85	94	trace →
10	GPT 5.5 (high)	96.0%	$2.63	36	trace →
11	Claude Opus 4.8 (xhigh)	96.0%	$25.00	151	trace →
12	Claude Opus 4.7	95.7%	$5.84	142	trace →
13	GPT-5.6 Sol (xhigh)	95.4%	$4.69	34	trace →
14	Gemini 3.7 Flash	94.7%	$2.15	130	trace →
15	Claude Opus 4.6	94.6%	$11.60	302	trace →
16	Claude Opus 4.7 (xhigh)	94.4%	$11.23	119	trace →
17	GPT-5.6 Sol	93.7%	$0.62	11	trace →
18	GLM-5.2	93.6%	$10.28	136	trace →
19	Muse Spark 1.1 (xhigh)	93.3%	$0.83	225	trace →
20	GPT 5.5	91.8%	$0.73	13	trace →
21	Gemini 3.5 Flash	91.2%	$4.42	177	trace →
22	Gemini 3.6 Flash	91.1%	$3.22	153	trace →
23	Claude Sonnet 4.6	87.5%	$15.93	374	trace →
24	GPT 5.4	86.8%	$0.25	10	trace →
25	GPT 5 mini	80.5%	$0.03	13	trace →
26	GPT 5.4 mini	69.5%	$0.03	9	trace →
27	Claude Haiku 4.5	64.9%	$0.57	107	trace →
28	Gemini 3.1 Pro	58.7%	$1.87	129	trace →
29	Gemini 3 Flash	3.3%	$0.33	114	trace →
30	Muse Spark 1.2 (xhigh)	0.0%	$1.06	161	trace →

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