sheepla/pingu | ProgramBench

🐧ping command but with pingu

378

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%	$4.20	66	trace →
2	Claude Fable 5.1 (xhigh)	100.0%	$7.58	69	trace →
3	GPT 6 Astra (max)	100.0%	$3.71	26	trace →
4	Muse Spark 1.3 (xhigh)	99.7%	$0.45	120	trace →
5	Claude Opus 4.7 (xhigh)	98.9%	$5.81	109	trace →
6	Muse Spark 1.2 (xhigh)	98.4%	$2.31	187	trace →
7	Gemini 3.7 Flash	97.9%	$0.75	55	trace →
8	Muse Wonder Full	97.6%	TBA	130	trace →
9	Muse Wonder (xhigh)	97.6%	$4.81	101	trace →
10	Claude Opus 4.8 (xhigh)	97.6%	$8.15	77	trace →
11	Claude Opus 4.7	96.8%	$3.36	104	trace →
12	Muse Spark 1.3 (max)	96.6%	$2.07	190	trace →
13	GPT-5.6 Sol (xhigh)	96.3%	$1.97	19	trace →
14	GPT 5.5 (xhigh)	96.3%	$4.39	45	trace →
15	GPT 5.5 (high)	96.0%	$2.73	35	trace →
16	GLM-5.2	95.4%	$9.15	110	trace →
17	Claude Opus 5 (xhigh)	95.0%	$8.03	74	trace →
18	GPT-5.6 Sol	94.7%	$0.88	16	trace →
19	Claude Opus 4.6	94.2%	$6.93	165	trace →
20	Gemini 3.6 Flash	93.1%	$3.32	101	trace →
21	Claude Sonnet 4.6	92.3%	$3.78	175	trace →
22	Gemini 3.5 Flash	91.3%	$2.95	96	trace →
23	GPT 5.5	87.8%	$0.93	19	trace →
24	Claude Haiku 4.5	73.5%	$0.48	87	trace →
25	GPT 5 mini	66.1%	$0.02	18	trace →
26	GPT 5.4	61.9%	$0.22	10	trace →
27	Gemini 3 Flash	58.7%	$0.30	59	trace →
28	GPT 5.4 mini	17.5%	$0.01	9	trace →
29	Muse Spark 1.1 (xhigh)	0.5%	$0.29	136	trace →
30	Gemini 3.1 Pro	0.0%	$1.11	48	trace →

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