sigoden/argc | ProgramBench

A Bash CLI framework, also a Bash command runner.

995

Generated Behavioral Tests

89.8%

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)	89.8%	$59.64	531	trace →
2	Claude Fable 5.1 (xhigh)	89.0%	$77.86	419	trace →
3	Muse Wonder Full	88.5%	TBA	795	trace →
4	Claude Opus 5 (xhigh)	85.4%	$119.80	534	trace →
5	GPT 6 Astra (max)	83.5%	$18.09	112	trace →
6	Muse Wonder (xhigh)	79.7%	$68.29	699	trace →
7	Muse Spark 1.3 (max)	72.0%	$9.13	465	trace →
8	GPT-5.6 Sol (xhigh)	62.0%	$10.74	52	trace →
9	Gemini 3.7 Flash	52.9%	$6.28	217	trace →
10	Claude Opus 4.8 (xhigh)	52.2%	$48.62	226	trace →
11	Claude Sonnet 4.6	44.1%	$79.14	919	trace →
12	GPT 5.5 (xhigh)	42.8%	$13.46	111	trace →
13	Claude Opus 4.6	39.8%	$30.14	435	trace →
14	Muse Spark 1.1 (xhigh)	39.7%	$0.28	204	trace →
15	Gemini 3.6 Flash	36.5%	$13.42	232	trace →
16	GPT 5.5 (high)	31.5%	$5.08	46	trace →
17	Claude Opus 4.7 (xhigh)	28.0%	$6.90	121	trace →
18	GLM-5.2	25.5%	$44.32	386	trace →
19	Gemini 3.5 Flash	22.2%	$5.78	213	trace →
20	GPT 5.5	18.4%	$2.18	29	trace →
21	Claude Haiku 4.5	10.4%	$1.47	175	trace →
22	GPT 5.4	10.3%	$0.55	16	trace →
23	Gemini 3 Flash	8.8%	$0.21	63	trace →
24	Claude Opus 4.7	7.9%	$0.61	34	trace →
25	GPT 5 mini	7.3%	$0.02	20	trace →
26	Gemini 3.1 Pro	7.1%	$1.30	88	trace →
27	GPT-5.6 Sol	0.5%	$1.53	25	trace →
28	Muse Spark 1.3 (xhigh)	0.4%	$2.89	348	trace →
29	Muse Spark 1.2 (xhigh)	0.4%	$3.23	195	trace →
30	GPT 5.4 mini	0.0%	$0.02	7	trace →

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