yaa110/nomino | ProgramBench

Batch rename utility for developers

313

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%	$7.91	184	trace →
2	Claude Fable 5.1 (xhigh)	100.0%	$14.94	172	trace →
3	Muse Wonder Full	100.0%	TBA	268	trace →
4	Muse Wonder (xhigh)	100.0%	$12.47	202	trace →
5	Muse Spark 1.3 (max)	100.0%	$3.22	249	trace →
6	GPT 6 Astra (max)	99.7%	$6.41	36	trace →
7	GLM-5.2	97.8%	$17.24	171	trace →
8	Claude Opus 4.8 (xhigh)	97.4%	$15.84	134	trace →
9	Muse Spark 1.3 (xhigh)	96.5%	$0.81	151	trace →
10	GPT-5.6 Sol (xhigh)	95.5%	$3.24	32	trace →
11	GPT 5.5 (xhigh)	94.2%	$5.15	70	trace →
12	Claude Opus 5 (xhigh)	92.3%	$24.36	204	trace →
13	Gemini 3.5 Flash	88.8%	$3.39	154	trace →
14	Muse Spark 1.2 (xhigh)	88.2%	$1.07	155	trace →
15	Muse Spark 1.1 (xhigh)	87.2%	$0.97	239	trace →
16	GPT 5.5 (high)	85.0%	$2.16	35	trace →
17	GPT-5.6 Sol	83.4%	$1.08	17	trace →
18	Gemini 3.7 Flash	83.4%	$1.03	132	trace →
19	GPT 5.5	83.4%	$1.30	27	trace →
20	Claude Sonnet 4.6	79.9%	$19.28	518	trace →
21	Claude Opus 4.7	79.6%	$4.21	119	trace →
22	Gemini 3.6 Flash	75.4%	$2.63	156	trace →
23	Claude Opus 4.6	72.2%	$10.11	270	trace →
24	Gemini 3 Flash	60.7%	$0.29	142	trace →
25	Gemini 3.1 Pro	53.7%	$1.54	170	trace →
26	GPT 5.4	51.4%	$0.30	15	trace →
27	Claude Haiku 4.5	29.1%	$0.66	114	trace →
28	GPT 5 mini	15.0%	$0.02	11	trace →
29	GPT 5.4 mini	5.1%	$0.05	16	trace →
30	Claude Opus 4.7 (xhigh)	2.9%	$16.99	247	trace →

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