ekzhang/bore | ProgramBench

🕳 bore is a simple CLI tool for making tunnels to localhost

393

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%	$14.97	203	trace →
2	Claude Fable 5.1 (xhigh)	100.0%	$21.29	185	trace →
3	Claude Opus 5 (xhigh)	100.0%	$19.96	173	trace →
4	GPT 6 Astra (max)	99.7%	$6.52	40	trace →
5	Muse Wonder (xhigh)	99.5%	$12.73	206	trace →
6	Claude Opus 4.8 (xhigh)	99.5%	$10.72	102	trace →
7	Muse Spark 1.3 (max)	99.2%	$3.07	184	trace →
8	Muse Spark 1.3 (xhigh)	99.2%	$0.82	151	trace →
9	GLM-5.2	99.0%	$16.22	174	trace →
10	Muse Wonder Full	98.7%	TBA	273	trace →
11	GPT-5.6 Sol (xhigh)	95.9%	$5.02	43	trace →
12	Claude Opus 4.7 (xhigh)	93.1%	$13.90	184	trace →
13	GPT 5.5 (high)	92.4%	$3.71	39	trace →
14	GPT 5.5 (xhigh)	85.8%	$4.88	60	trace →
15	Gemini 3.5 Flash	82.2%	$3.45	115	trace →
16	Gemini 3.7 Flash	81.7%	$2.07	141	trace →
17	Gemini 3.6 Flash	80.4%	$3.47	134	trace →
18	Claude Opus 4.7	74.6%	$5.59	112	trace →
19	Muse Spark 1.2 (xhigh)	71.8%	$0.23	170	trace →
20	Muse Spark 1.1 (xhigh)	71.8%	$0.61	259	trace →
21	Claude Opus 4.6	68.7%	$8.20	193	trace →
22	GPT 5.5	65.4%	$1.79	28	trace →
23	GPT-5.6 Sol	53.4%	$0.38	9	trace →
24	Claude Sonnet 4.6	48.1%	$8.25	225	trace →
25	Gemini 3.1 Pro	43.8%	$1.28	70	trace →
26	GPT 5.4	42.0%	$0.56	14	trace →
27	Claude Haiku 4.5	33.6%	$0.54	117	trace →
28	Gemini 3 Flash	28.5%	$0.28	81	trace →
29	GPT 5 mini	11.7%	$0.02	16	trace →
30	GPT 5.4 mini	11.5%	$0.04	11	trace →

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