AutoExacto Benchmarks
GPQA Diamond
TAU-Bench
Baseten
89.3%
--
Fireworks
88.9%
--
Baseten
88.0%
--
DeepSeek
90.2%
81.3%
NextBit
89.9%
76.6%
Alibaba Cloud Int.
89.4%
76.8%
+30 more providers

---- dialog ----

Responses are AI-generated. Verify before relying on them.

AutoExacto Benchmarks
Rolling average over the past 32 days — the same lookback window used for quality-based routing
Learn more
	Provider	GPQA Diamond	TAU-Bench Airline

	Baseten	89.3%	--

	Fireworks	88.9%	--

	Baseten	88.0%	--

	DeepSeek	90.2%	81.3%

	NextBit	89.9%	76.6%

	Alibaba Cloud Int.	89.4%	76.8%

	SiliconFlow	90.0%	75.4%

	NovitaAI	89.3%	76.0%

	Ionstream	87.2%	78.0%

	GMICloud	89.0%	75.8%

	Reka AI	89.1%	75.4%

	Parasail	89.0%	75.4%

	Baidu Qianfan	89.6%	74.8%

	Cloudflare	88.4%	75.0%

	CoreWeave	87.1%	76.0%

	DeepInfra	89.2%	73.9%

	StreamLake	87.8%	74.9%

	Phala	88.2%	74.5%

	Inceptron	87.9%	74.1%

	AtlasCloud	88.3%	73.6%

	Together	86.9%	75.0%

	Decart	87.9%	73.3%

	Venice	86.8%	74.2%

	AkashML	88.5%	72.5%

	Morph	85.8%	74.9%

	Wafer	84.1%	76.0%

	Ambient	86.4%	73.5%

	Relace	87.2%	71.7%

	Io Net	84.1%	74.5%

	Makora	86.9%	71.7%

	Mancer	85.5%	70.8%

	auto-routing	84.8%	70.8%

	Sail Research	70.8%	75.2%

	OpenInference	70.5%	70.8%

	Nebius	75.6%	65.3%

	DigitalOcean	75.3%	58.4%
Close