orf/gping | ProgramBench

Ping, but with a graph

338

Generated Behavioral Tests

99.4%

Best Score

Muse Wonder Full

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	Muse Wonder Full	99.4%	TBA	329	trace →
2	GPT 6 Astra (max)	99.1%	$9.74	51	trace →
3	Claude Opus 5.5 (xhigh)	97.9%	$16.66	203	trace →
4	Claude Fable 5.1 (xhigh)	97.3%	$36.97	278	trace →
5	Claude Opus 5 (xhigh)	97.3%	$58.88	294	trace →
6	Muse Wonder (xhigh)	96.7%	$35.68	367	trace →
7	Muse Spark 1.3 (max)	95.9%	$4.45	271	trace →
8	Claude Opus 4.8 (xhigh)	95.0%	$20.74	134	trace →
9	Gemini 3.6 Flash	91.4%	$2.43	111	trace →
10	GLM-5.2	91.1%	$20.13	168	trace →
11	GPT 5.5 (xhigh)	88.5%	$8.13	76	trace →
12	GPT 5.5 (high)	85.5%	$3.77	49	trace →
13	Muse Spark 1.2 (xhigh)	85.5%	$0.59	129	trace →
14	GPT-5.6 Sol (xhigh)	84.9%	$4.00	25	trace →
15	Muse Spark 1.3 (xhigh)	83.7%	$1.27	200	trace →
16	GPT-5.6 Sol	80.5%	$1.47	23	trace →
17	Gemini 3.7 Flash	80.5%	$1.16	127	trace →
18	Muse Spark 1.1 (xhigh)	80.5%	$0.37	136	trace →
19	Claude Opus 4.6	79.0%	$10.87	211	trace →
20	Claude Opus 4.7 (xhigh)	77.5%	$5.92	120	trace →
21	Claude Opus 4.7	72.5%	$1.89	70	trace →
22	GPT 5.5	68.9%	$0.82	16	trace →
23	Claude Sonnet 4.6	58.3%	$11.38	271	trace →
24	Gemini 3.5 Flash	56.5%	$4.22	109	trace →
25	GPT 5.4	49.1%	$0.18	8	trace →
26	Gemini 3.1 Pro	37.0%	$0.66	33	trace →
27	Gemini 3 Flash	29.6%	$0.22	64	trace →
28	GPT 5 mini	21.9%	$0.01	7	trace →
29	GPT 5.4 mini	21.0%	$0.03	18	trace →
30	Claude Haiku 4.5	16.3%	$0.48	113	trace →

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