elkowar/pipr | ProgramBench

A tool to interactively write shell pipelines.

524

Generated Behavioral Tests

99.2%

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)	99.2%	$53.71	451	trace →
2	Muse Wonder Full	96.6%	TBA	713	trace →
3	Claude Opus 5 (xhigh)	94.8%	$84.89	431	trace →
4	Muse Wonder (xhigh)	93.9%	$53.15	493	trace →
5	Claude Fable 5.1 (xhigh)	93.3%	$40.56	332	trace →
6	GPT 6 Astra (max)	91.4%	$7.58	52	trace →
7	Claude Opus 4.8 (xhigh)	86.6%	$24.83	193	trace →
8	Muse Spark 1.3 (max)	85.5%	$7.65	344	trace →
9	Gemini 3.7 Flash	78.8%	$2.63	161	trace →
10	GPT-5.6 Sol (xhigh)	74.4%	$4.63	36	trace →
11	Muse Spark 1.3 (xhigh)	68.1%	$1.09	215	trace →
12	Claude Opus 4.7 (xhigh)	67.2%	$12.21	249	trace →
13	GPT 5.5 (xhigh)	64.7%	$7.60	62	trace →
14	GLM-5.2	60.5%	$23.54	287	trace →
15	Muse Spark 1.1 (xhigh)	59.2%	$0.25	81	trace →
16	GPT 5.5 (high)	58.0%	$3.22	34	trace →
17	Muse Spark 1.2 (xhigh)	57.3%	$0.15	147	trace →
18	Claude Opus 4.7	57.3%	$3.08	108	trace →
19	Gemini 3.6 Flash	55.3%	$3.60	134	trace →
20	GPT-5.6 Sol	55.0%	$1.02	16	trace →
21	Gemini 3.5 Flash	54.2%	$4.19	145	trace →
22	Claude Opus 4.6	53.8%	$10.10	210	trace →
23	GPT 5.5	53.2%	$0.98	19	trace →
24	Gemini 3.1 Pro	46.2%	$2.81	138	trace →
25	GPT 5.4	33.4%	$0.11	11	trace →
26	GPT 5.4 mini	31.9%	$0.02	7	trace →
27	Claude Haiku 4.5	24.8%	$0.58	119	trace →
28	Gemini 3 Flash	5.7%	$0.30	87	trace →
29	Claude Sonnet 4.6	2.9%	$22.65	354	trace →
30	GPT 5 mini	2.5%	$0.01	10	trace →

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