The devtools AI chooses.

We give LLMs the same app-building prompts, then rank the tools they recommend.

Ranked by recommendations from

Loading model recommendations…

#	Tool	Support Rate	95% CI	Models	Prompts
1	BRBraintrust	34.8%(1577/4528)	33-36%	80%	100%
2	LALangSmith	29.5%(1338/4528)	28-31%	75%	100%
3	RARagas	4.7%(215/4528)	4-5%	70%	92%
4	DEDeepEval	4.0%(179/4528)	3-5%	20%	100%
5	ARArize AI	3.3%(148/4528)	3-4%	30%	92%
6	PRPromptfoo	2.7%(123/4528)	2-3%	57%	100%
7	WEWeights & Biases	2.7%(122/4528)	2-3%	18%	67%
8	LALangfuse	2.3%(103/4528)	2-3%	43%	92%
9	LALangChain	1.9%(84/4528)	2-2%	15%	75%
10	HUHumanFirst	1.3%(58/4528)	1-2%	3%	67%
11	HUHumanloop	1.2%(56/4528)	1-2%	20%	67%
12	OPOpenAI	1.1%(48/4528)	1-1%	18%	75%
13	LLLlamaIndex	0.8%(38/4528)	1-1%	3%	67%
14	ARArize Phoenix	0.8%(37/4528)	1-1%	18%	67%
15	MLMLflow	0.6%(25/4528)	0-1%	3%	58%
16	TRTruLens	0.5%(23/4528)	0-1%	10%	75%
17	VEVellum	0.4%(19/4528)	0-1%	5%	33%
18	TRTruEra	0.4%(16/4528)	0-1%	10%	58%
19	LMLMSYS Chatbot Arena	0.3%(15/4528)	0-1%	3%	67%
20	UPUpTrain	0.3%(12/4528)	0-0%	5%	42%
21	DADatadog	0.2%(11/4528)	0-0%	5%	25%
22	OPOpenEvals	0.2%(8/4528)	0-0%	3%	25%
23	HEHelicone	0.2%(7/4528)	0-0%	8%	25%
24	PAPatronus AI	0.2%(7/4528)	0-0%	8%	25%
25	LALangCheck	0.1%(5/4528)	0-0%	3%	25%
26	GAGalileo	0.1%(4/4528)	0-0%	5%	33%
27	FIFireflies.ai	0.1%(3/4528)	0-0%	3%	8%
28	PHPhoenix	0.1%(3/4528)	0-0%	3%	25%
29	GRGreat Expectations	0.0%(2/4528)	0-0%	3%	8%
30	GCGCP Vertex AI	0.0%(1/4528)	0-0%	3%	8%
31	HUHugging Face	0.0%(1/4528)	0-0%	3%	8%
32	INIntercom	0.0%(1/4528)	0-0%	3%	8%
33	PRPromptLayer	0.0%(1/4528)	0-0%	3%	8%
34	ZEZendesk	0.0%(1/4528)	0-0%	3%	8%

#	Tool	Support Rate	95% CI	Models	Prompts
1	BRBraintrust	34.8%(1577/4528)	33-36%	80%	100%
2	LALangSmith	29.5%(1338/4528)	28-31%	75%	100%
3	RARagas	4.7%(215/4528)	4-5%	70%	92%
4	DEDeepEval	4.0%(179/4528)	3-5%	20%	100%
5	ARArize AI	3.3%(148/4528)	3-4%	30%	92%
6	PRPromptfoo	2.7%(123/4528)	2-3%	57%	100%
7	WEWeights & Biases	2.7%(122/4528)	2-3%	18%	67%
8	LALangfuse	2.3%(103/4528)	2-3%	43%	92%
9	LALangChain	1.9%(84/4528)	2-2%	15%	75%
10	HUHumanFirst	1.3%(58/4528)	1-2%	3%	67%
11	HUHumanloop	1.2%(56/4528)	1-2%	20%	67%
12	OPOpenAI	1.1%(48/4528)	1-1%	18%	75%
13	LLLlamaIndex	0.8%(38/4528)	1-1%	3%	67%
14	ARArize Phoenix	0.8%(37/4528)	1-1%	18%	67%
15	MLMLflow	0.6%(25/4528)	0-1%	3%	58%
16	TRTruLens	0.5%(23/4528)	0-1%	10%	75%
17	VEVellum	0.4%(19/4528)	0-1%	5%	33%
18	TRTruEra	0.4%(16/4528)	0-1%	10%	58%
19	LMLMSYS Chatbot Arena	0.3%(15/4528)	0-1%	3%	67%
20	UPUpTrain	0.3%(12/4528)	0-0%	5%	42%
21	DADatadog	0.2%(11/4528)	0-0%	5%	25%
22	OPOpenEvals	0.2%(8/4528)	0-0%	3%	25%
23	HEHelicone	0.2%(7/4528)	0-0%	8%	25%
24	PAPatronus AI	0.2%(7/4528)	0-0%	8%	25%
25	LALangCheck	0.1%(5/4528)	0-0%	3%	25%
26	GAGalileo	0.1%(4/4528)	0-0%	5%	33%
27	FIFireflies.ai	0.1%(3/4528)	0-0%	3%	8%
28	PHPhoenix	0.1%(3/4528)	0-0%	3%	25%
29	GRGreat Expectations	0.0%(2/4528)	0-0%	3%	8%
30	GCGCP Vertex AI	0.0%(1/4528)	0-0%	3%	8%
31	HUHugging Face	0.0%(1/4528)	0-0%	3%	8%
32	INIntercom	0.0%(1/4528)	0-0%	3%	8%
33	PRPromptLayer	0.0%(1/4528)	0-0%	3%	8%
34	ZEZendesk	0.0%(1/4528)	0-0%	3%	8%

Rankings