robertdavidgraham/masscan

TCP port scanner, spews SYN packets asynchronously, scanning entire Internet in under 5 minutes.

2,549

Generated Behavioral Tests

97.8%

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)	97.8%	$49.85	448	trace →
2	Muse Wonder Full	91.6%	TBA	482	trace →
3	Claude Opus 5 (xhigh)	90.2%	$50.41	302	trace →
4	GPT 6 Astra (max)	89.7%	$11.82	60	trace →
5	Muse Wonder (xhigh)	88.7%	$86.17	678	trace →
6	Muse Spark 1.3 (max)	76.9%	$5.03	300	trace →
7	GPT-5.6 Sol (xhigh)	73.2%	$5.52	36	trace →
8	Muse Spark 1.3 (xhigh)	73.1%	$1.02	167	trace →
9	Claude Opus 4.8 (xhigh)	67.4%	$12.75	150	trace →
10	GPT 5.5 (xhigh)	65.8%	$8.94	74	trace →
11	Gemini 3.6 Flash	65.6%	$3.58	129	trace →
12	Muse Spark 1.2 (xhigh)	62.8%	$6.91	357	trace →
13	GPT-5.6 Sol	59.0%	$1.03	11	trace →
14	Claude Opus 4.6	56.9%	$13.59	295	trace →
15	Muse Spark 1.1 (xhigh)	56.3%	$0.16	156	trace →
16	GLM-5.2	55.6%	$21.04	167	trace →
17	GPT 5.5 (high)	53.7%	$5.02	40	trace →
18	Gemini 3.1 Pro	52.6%	$1.58	100	trace →
19	Gemini 3 Flash	52.4%	$0.26	85	trace →
20	Claude Opus 4.7	50.6%	$1.13	49	trace →
21	Claude Sonnet 4.6	48.8%	$14.79	500	trace →
22	GPT 5.5	46.3%	$1.30	19	trace →
23	Gemini 3.5 Flash	44.3%	$4.90	227	trace →
24	GPT 5.4	40.7%	$0.24	9	trace →
25	Claude Opus 4.7 (xhigh)	38.4%	$4.48	109	trace →
26	Claude Haiku 4.5	30.2%	$1.65	197	trace →
27	GPT 5 mini	21.3%	$0.02	15	trace →
28	GPT 5.4 mini	18.4%	$0.03	8	trace →
29	Claude Fable 5.1 (xhigh)	0.0%	$0.15	5	trace →
30	Gemini 3.7 Flash	0.0%	$1.09	119	trace →

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