hairyhenderson/gomplate

A flexible commandline tool for template rendering. Supports lots of local and remote datasources.

2,926

Generated Behavioral Tests

97.6%

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)	97.6%	$42.05	330	trace →
2	Muse Wonder Full	97.4%	TBA	708	trace →
3	Claude Fable 5.1 (xhigh)	96.3%	$60.44	269	trace →
4	Muse Wonder (xhigh)	93.0%	$51.88	493	trace →
5	GPT 6 Astra (max)	93.0%	$18.50	75	trace →
6	Claude Opus 5 (xhigh)	91.2%	$42.53	246	trace →
7	GPT-5.6 Sol (xhigh)	84.1%	$13.16	87	trace →
8	Gemini 3.7 Flash	79.9%	$2.58	192	trace →
9	Muse Spark 1.3 (max)	79.3%	$10.12	415	trace →
10	Claude Opus 4.8 (xhigh)	79.2%	$26.15	183	trace →
11	Muse Spark 1.3 (xhigh)	78.3%	$1.86	257	trace →
12	Claude Sonnet 4.6	74.7%	$22.13	450	trace →
13	GPT 5.5 (high)	71.8%	$5.18	46	trace →
14	Muse Spark 1.2 (xhigh)	71.0%	$0.85	172	trace →
15	Claude Opus 4.6	70.9%	$14.37	258	trace →
16	GLM-5.2	68.9%	$27.00	219	trace →
17	Muse Spark 1.1 (xhigh)	67.4%	$3.20	294	trace →
18	Gemini 3.6 Flash	65.4%	$4.87	145	trace →
19	Claude Opus 4.7 (xhigh)	57.6%	$6.97	133	trace →
20	GPT 5.5 (xhigh)	54.7%	$8.30	70	trace →
21	GPT 5.5	52.1%	$1.56	22	trace →
22	Gemini 3.5 Flash	52.1%	$6.70	180	trace →
23	Claude Opus 4.7	41.1%	$4.69	89	trace →
24	GPT-5.6 Sol	36.5%	$1.39	18	trace →
25	GPT 5.4	19.3%	$0.46	12	trace →
26	Gemini 3 Flash	17.1%	$0.24	89	trace →
27	Claude Haiku 4.5	14.4%	$0.48	98	trace →
28	GPT 5 mini	10.4%	$0.02	17	trace →
29	GPT 5.4 mini	8.6%	$0.05	10	trace →
30	Gemini 3.1 Pro	0.0%	$0.90	86	trace →

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