BurntSushi/ripgrep | ProgramBench

ripgrep recursively searches directories for a regex pattern while respecting your gitignore

1,992

Generated Behavioral Tests

99.8%

Best Score

Claude Fable 5.1 (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 Fable 5.1 (xhigh)	99.8%	$117.62	284	trace →
2	Muse Wonder (xhigh)	98.8%	$115.92	861	trace →
3	Claude Opus 5.5 (xhigh)	98.6%	$47.08	371	trace →
4	Muse Wonder Full	98.1%	TBA	515	trace →
5	Claude Opus 5 (xhigh)	97.7%	$126.57	413	trace →
6	GPT 6 Astra (max)	97.5%	$11.83	56	trace →
7	Muse Spark 1.3 (max)	92.0%	$3.42	266	trace →
8	GPT 5.5 (xhigh)	84.0%	$17.56	121	trace →
9	Claude Sonnet 4.6	79.7%	$19.39	508	trace →
10	Muse Spark 1.3 (xhigh)	78.5%	$1.17	213	trace →
11	Claude Opus 4.8 (xhigh)	78.0%	$23.89	158	trace →
12	Muse Spark 1.2 (xhigh)	76.2%	$0.38	120	trace →
13	GPT-5.6 Sol (xhigh)	75.9%	$7.13	42	trace →
14	GLM-5.2	70.7%	$20.64	271	trace →
15	GPT 5.5 (high)	70.5%	$3.00	28	trace →
16	GPT-5.6 Sol	67.4%	$1.04	15	trace →
17	Gemini 3.6 Flash	67.0%	$5.01	184	trace →
18	Gemini 3.7 Flash	67.0%	$1.11	151	trace →
19	GPT 5.5	66.0%	$1.27	18	trace →
20	Claude Opus 4.7 (xhigh)	62.4%	$6.75	168	trace →
21	Gemini 3.5 Flash	50.0%	$4.23	146	trace →
22	Claude Opus 4.7	40.7%	$2.47	75	trace →
23	GPT 5.4	35.5%	$0.26	7	trace →
24	Gemini 3 Flash	35.1%	$0.25	77	trace →
25	Gemini 3.1 Pro	29.7%	$1.35	103	trace →
26	GPT 5 mini	27.7%	$0.03	18	trace →
27	Claude Haiku 4.5	23.7%	$0.88	118	trace →
28	Muse Spark 1.1 (xhigh)	2.3%	$0.20	138	trace →
29	GPT 5.4 mini	0.2%	$0.01	11	trace →
30	Claude Opus 4.6	0.0%	$2.74	261	trace →

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