LuaJIT/LuaJIT | ProgramBench

Mirror of the LuaJIT git repository

2,967

Generated Behavioral Tests

98.2%

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)	98.2%	$63.34	362	trace →
2	Muse Wonder Full	97.6%	TBA	372	trace →
3	GPT 6 Astra (max)	96.5%	$19.40	53	trace →
4	Muse Wonder (xhigh)	93.0%	$21.40	236	trace →
5	Claude Fable 5.1 (xhigh)	87.3%	$65.26	265	trace →
6	Muse Spark 1.3 (max)	84.0%	$7.08	325	trace →
7	GPT-5.6 Sol (xhigh)	82.4%	$6.13	47	trace →
8	Muse Spark 1.3 (xhigh)	79.5%	$1.54	243	trace →
9	GPT 5.5 (xhigh)	78.0%	$8.42	68	trace →
10	Claude Opus 4.8 (xhigh)	73.9%	$23.18	138	trace →
11	Claude Sonnet 4.6	71.5%	$31.45	520	trace →
12	GPT 5.5 (high)	65.5%	$2.54	26	trace →
13	Claude Opus 4.7 (xhigh)	58.4%	$8.01	142	trace →
14	GPT-5.6 Sol	57.9%	$0.74	13	trace →
15	Muse Spark 1.2 (xhigh)	53.5%	$1.20	135	trace →
16	GLM-5.2	52.3%	$56.68	302	trace →
17	Gemini 3.6 Flash	44.5%	$3.34	143	trace →
18	GPT 5.5	33.9%	$1.10	15	trace →
19	Claude Opus 4.6	29.0%	$19.88	259	trace →
20	Gemini 3.5 Flash	25.6%	$4.40	129	trace →
21	Gemini 3 Flash	19.4%	$0.15	68	trace →
22	GPT 5 mini	14.6%	$0.01	8	trace →
23	GPT 5.4	7.7%	$0.18	16	trace →
24	GPT 5.4 mini	5.3%	$0.02	9	trace →
25	Muse Spark 1.1 (xhigh)	3.6%	$1.87	439	trace →
26	Gemini 3.1 Pro	3.6%	$1.22	122	trace →
27	Claude Opus 4.7	2.9%	$0.33	18	trace →
28	Claude Haiku 4.5	1.2%	$0.98	157	trace →
29	Gemini 3.7 Flash	1.1%	$0.91	82	trace →
30	Claude Opus 5 (xhigh)	0.0%	$3.84	56	trace →

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