User Leaderboard

Every run. Every user.

428 submissions from 52 users. Sort, filter, find someone who ran your model.

Want on the board? Run the CLI.

Filter

All alibaba bigcode cohere community databricks deepseek google internlm meta microsoft mistral moonshot nous xai yi zhipu|TRUNK MAINLINE FEEDER TAP DRIP|Lab-verified only

#	User ↕	Model ↕	Provider ↕	Hardware	Config	Score ↓	Tier ↕	Latency	Date ↕
101	labLab	Hermes 3 Llama 3.1 70B	nous	lab-m2-ultra-192gb	base	78.0	MAINLINE	3,000ms	2026-04-10
102	labLab	GLM 4 Plus	zhipu	lab-dgx-h100	base	77.9	MAINLINE	910ms	2026-04-22
103	labLab	Codestral 22B	mistral	lab-rtx-3090-24gb	base	77.9	MAINLINE	1,481ms	2026-04-18
104	mlx-mike	WizardLM 2 8x22B	microsoft	h200-141gb	base	77.8	MAINLINE	880ms	2026-05-15
105	frontiermodel	Mistral Large 2	mistral	—	base	77.8	MAINLINE	819ms	2026-05-20
106	flash-attn-fan	Gemma 3 27B IT	google	rtx-4090-24gb	base	77.7	MAINLINE	1,466ms	2026-04-24
107	bench-rat	Qwen 2.5 VL 72B	alibaba	a100-80gb	base	77.7	MAINLINE	889ms	2026-04-12
108	haiku_or_die	Mistral Large 2	mistral	rtx-4090-24gb	base	77.5	MAINLINE	783ms	2026-05-16
109	rocm-rider	DeepSeek V2.5	deepseek	a100-80gb	base	77.5	MAINLINE	899ms	2026-05-16
110	cpu-only-prophet	DeepSeek V2.5	deepseek	h200-141gb	base	77.4	MAINLINE	826ms	2026-05-20
111	mlx-mike	Mixtral 8x22B Instruct	mistral	b200-192gb	base	77.4	MAINLINE	912ms	2026-04-17
112	cuda-cult	Command A	cohere	m3-ultra-256gb	base	77.4	MAINLINE	2,884ms	2026-05-23
113	agentic_dad	Mistral Large 2	mistral	rtx-4090-24gb	cot-style	77.3	MAINLINE	888ms	2026-05-08
114	localmodels	Mistral Large 2	mistral	rtx-4090-24gb	cot-style	77.3	MAINLINE	758ms	2026-05-23
115	inference-monk	Hermes 3 Llama 3.1 70B	nous	m3-ultra-256gb	base	77.2	MAINLINE	2,907ms	2026-05-14
116	bench-rat	Qwen 3 32B Instruct	alibaba	rtx-3090-24gb	base	77.0	MAINLINE	1,546ms	2026-04-18
117	rig-tester	Kimi K2 Instruct	moonshot	m3-ultra-256gb	base	77.0	MAINLINE	3,041ms	2026-04-23
118	labLab	Qwen 2.5 14B Instruct	alibaba	lab-ryzen-7950x-cpu-only	base	76.9	MAINLINE	767ms	2026-05-15
119	quant-or-die	Qwen 2.5 VL 72B	alibaba	h100-80gb	base	76.9	MAINLINE	837ms	2026-05-18
120	gguf-pilgrim	Gemma 3 27B IT	google	rtx-3090-24gb	base	76.9	MAINLINE	1,506ms	2026-05-02
121	rocm-rider	DeepSeek Coder V2 16B	deepseek	a6000-48gb	base	76.9	MAINLINE	1,510ms	2026-04-18
122	mlx-mike	Codestral 22B	mistral	m3-max-128gb	base	76.9	MAINLINE	1,505ms	2026-05-14
123	mac-stack	Llama 3.3 70B Instruct	meta	m3-ultra-256gb	base	76.9	MAINLINE	3,001ms	2026-04-24
124	vram-monk	Magnum V4 72B	community	a100-80gb	base	76.8	MAINLINE	923ms	2026-05-07
125	labLab	Llama 3.1 70B Instruct	meta	lab-dgx-h100	base	76.8	MAINLINE	884ms	2026-04-29
126	labLab	Devstral Small 24B	mistral	lab-a6000-48gb	base	76.7	MAINLINE	1,523ms	2026-04-20
127	rig-tester	DeepSeek V2.5	deepseek	m2-ultra-192gb	base	76.6	MAINLINE	3,032ms	2026-04-18
128	sram-hoarder	GLM 4 Plus	zhipu	a100-80gb	base	76.5	MAINLINE	880ms	2026-04-17
129	cuda-cult	Command A	cohere	2x-rtx-4090	base	76.5	MAINLINE	3,099ms	2026-05-24
130	rocm-rider	Kimi K2 Instruct	moonshot	dgx-h100	base	76.4	MAINLINE	905ms	2026-04-26
131	labLab	Qwen 2.5 32B Instruct	alibaba	lab-a100-40gb	base	76.3	MAINLINE	611ms	2026-04-16
132	mac-stack	Qwen 3 32B Instruct	alibaba	a6000-48gb	base	76.3	MAINLINE	1,462ms	2026-05-02
133	quant-or-die	Llama 3.1 70B Instruct	meta	h200-141gb	base	76.0	MAINLINE	944ms	2026-05-09
134	local-llama-fan	Qwen 2.5 32B Instruct	alibaba	m3-max-128gb	base	76.0	MAINLINE	1,563ms	2026-04-10
135	sram-hoarder	Gemma 3 27B IT	google	m3-max-64gb	base	75.9	MAINLINE	1,492ms	2026-05-11
136	labLab	Yi 1.5 34B Chat	yi	lab-rtx-3090-24gb	base	75.8	MAINLINE	1,501ms	2026-05-08
137	local-llama-fan	Gemma 3 12B IT	google	m2-pro-16gb	base	75.7	MAINLINE	783ms	2026-04-10
138	gguf-pilgrim	Devstral Small 24B	mistral	rtx-4080-16gb-offload	base	75.6	MAINLINE	1,575ms	2026-05-08
139	tensor-tomas	GLM 4 Plus	zhipu	b200-192gb	base	75.6	MAINLINE	915ms	2026-05-19
140	tps-counter	Qwen 2.5 Coder 7B	alibaba	rtx-3080-10gb	base	75.5	MAINLINE	808ms	2026-04-21
141	labLab	DeepSeek R1 Distill Llama 8B	deepseek	lab-macbook-pro-m3-pro-18gb	base	75.3	MAINLINE	788ms	2026-04-12
142	mac-stack	Magnum V4 72B	community	cloud-api	base	75.3	MAINLINE	950ms	2026-04-11
143	rocm-rider	Llama 3.1 70B Instruct	meta	a100-80gb	base	75.2	MAINLINE	851ms	2026-05-07
144	local-llama-fan	Qwen 2.5 14B Instruct	alibaba	rtx-3060-12gb	base	75.2	MAINLINE	761ms	2026-04-21
145	mac-stack	GLM 4 Plus	zhipu	m2-ultra-192gb	base	74.8	FEEDER	3,104ms	2026-05-12
146	mlx-mike	Qwen 3 14B Instruct	alibaba	rtx-3060-12gb	base	74.8	FEEDER	834ms	2026-04-19
147	gguf-pilgrim	Mixtral 8x22B Instruct	mistral	cloud-api	base	74.7	FEEDER	945ms	2026-04-23
148	cpu-only-prophet	Qwen 2.5 14B Instruct	alibaba	rtx-4070-12gb	base	74.7	FEEDER	840ms	2026-04-18
149	gguf-pilgrim	Gemma 2 27B IT	google	rtx-4090-24gb	base	74.7	FEEDER	1,431ms	2026-04-21
150	rig-tester	DeepSeek R1 Distill Llama 8B	deepseek	rtx-3080-10gb	base	74.6	FEEDER	811ms	2026-04-24
151	rig-tester	Codestral 22B	mistral	rtx-4090-24gb	base	74.6	FEEDER	1,495ms	2026-04-20
152	benchmark-rat	Llama 4 405B	meta	ryzen-7950x-cpu-only	base	74.6	FEEDER	943ms	2026-05-06
153	tps-counter	Magnum V4 72B	community	b200-192gb	base	74.5	FEEDER	887ms	2026-04-16
154	mac-stack	Devstral Small 24B	mistral	rtx-3090-24gb	base	74.5	FEEDER	1,622ms	2026-04-29
155	bench-rat	WizardLM 2 8x22B	microsoft	2x-rtx-4090	base	74.5	FEEDER	3,039ms	2026-04-26
156	labLab	Qwen 3 14B Instruct	alibaba	lab-rtx-3080-10gb	base	74.2	FEEDER	738ms	2026-04-20
157	rig-tester	DeepSeek Coder V2 16B	deepseek	m3-max-128gb	base	74.1	FEEDER	1,542ms	2026-05-09
158	gpu-shopper	Aya 23 35B	cohere	m3-max-64gb	base	74.1	FEEDER	1,547ms	2026-04-14
159	gemini-fan	Llama 4 405B	meta	—	lora-domain-finance	74.0	FEEDER	722ms	2026-05-02
160	rocm-rider	DeepSeek Coder V2 16B	deepseek	m3-max-64gb	base	74.0	FEEDER	1,479ms	2026-05-10
161	tps-counter	Qwen 2.5 32B Instruct	alibaba	a6000-48gb	base	73.9	FEEDER	1,590ms	2026-04-19
162	apple-silicon	Kimi K2 Instruct	moonshot	2x-rtx-4090	base	73.9	FEEDER	2,934ms	2026-05-20
163	quant-or-die	DBRX Instruct 132B-MoE	databricks	cloud-api	base	73.8	FEEDER	871ms	2026-04-12
164	gpt-cynic	Llama 4 405B	meta	h100-80gb	base	73.7	FEEDER	1,003ms	2026-05-05
165	karpathy_lite	Llama 4 405B	meta	m2-ultra-192gb	base	73.6	FEEDER	779ms	2026-05-19
166	labLab	Llama 4 405B	meta	lab-baseline	base	73.6	FEEDER	863ms	2026-05-16
167	tps-counter	Gemma 2 27B IT	google	a6000-48gb	base	73.5	FEEDER	1,441ms	2026-04-22
168	labLab	DeepSeek Coder V2 16B	deepseek	lab-rtx-3090-24gb	base	73.4	FEEDER	1,436ms	2026-04-22
169	rocm-rider	Codestral 22B	mistral	ryzen-7950x-rtx-3090	base	73.4	FEEDER	1,507ms	2026-05-06
170	labLab	Gemma 3 27B IT	google	lab-m3-max-128gb	base	73.4	FEEDER	1,555ms	2026-04-10
171	labLab	Gemma 2 27B IT	google	lab-m3-max-64gb	base	73.3	FEEDER	1,514ms	2026-04-12
172	inference-monk	Mistral Small 24B Instruct	mistral	rtx-4080-16gb-offload	base	73.2	FEEDER	1,458ms	2026-05-03
173	inference-monk	Gemma 3 12B IT	google	m3-pro-36gb	base	73.2	FEEDER	777ms	2026-04-25
174	tool-caller	Llama 4 405B	meta	m3-max-128gb	temp-zero	73.1	FEEDER	826ms	2026-05-07
175	labLab	DBRX Instruct 132B-MoE	databricks	lab-h100-80gb	base	73.1	FEEDER	921ms	2026-05-10
176	mac-stack	InternLM 2.5 20B Chat	internlm	rtx-4080-16gb-offload	base	73.0	FEEDER	1,495ms	2026-05-23
177	devnull	Llama 4 405B	meta	m3-max-128gb	base	72.9	FEEDER	758ms	2026-05-13
178	labLab	StarCoder2 15B	bigcode	lab-macbook-pro-m3-pro-18gb	base	72.7	FEEDER	788ms	2026-04-16
179	mlx-mike	Yi 1.5 34B Chat	yi	a100-40gb	base	72.7	FEEDER	624ms	2026-04-26
180	rig-tester	Qwen 2.5 14B Instruct	alibaba	m2-pro-16gb	base	72.7	FEEDER	800ms	2026-05-08
181	labLab	Qwen 3 8B Instruct	alibaba	lab-m2-pro-16gb	base	72.6	FEEDER	797ms	2026-04-19
182	mac-stack	L3 70B Euryale	community	4x-rtx-3090	base	72.4	FEEDER	3,022ms	2026-05-23
183	sram-hoarder	Phi 3.5 MoE 42B	microsoft	rtx-3090-24gb	base	72.3	FEEDER	1,434ms	2026-05-04
184	labLab	Phi 4 14B	microsoft	lab-macbook-pro-m3-pro-18gb	base	72.3	FEEDER	839ms	2026-04-28
185	karpathy_lite	Llama 4 405B	meta	a100-80gb	temp-zero	72.2	FEEDER	827ms	2026-05-04
186	dr_inference	Llama 4 405B	meta	rtx-4090-24gb	base	72.2	FEEDER	765ms	2026-05-16
187	mlx-mike	Yi 1.5 34B Chat	yi	m3-max-64gb	base	72.2	FEEDER	1,520ms	2026-05-21
188	labLab	Gemma 3 12B IT	google	lab-rtx-4080-16gb	base	72.2	FEEDER	781ms	2026-05-03
189	pipelinepilot	Command R+	cohere	rtx-3080-10gb	tools-enabled	72.1	FEEDER	875ms	2026-05-13
190	rust_witch	Llama 4 405B	meta	rtx-3090-24gb	lora-domain-finance	72.0	FEEDER	714ms	2026-05-13
191	reason-first	Command R+	cohere	—	base	72.0	FEEDER	684ms	2026-05-09
192	benchmark-rat	Command R+	cohere	m4-pro-48gb	base	71.9	FEEDER	754ms	2026-04-29
193	labLab	Command R+	cohere	lab-baseline	base	71.8	FEEDER	694ms	2026-05-02
194	tokenwrangler	Llama 4 405B	meta	m3-max-128gb	base	71.8	FEEDER	781ms	2026-05-12
195	rust_witch	Llama 4 405B	meta	ryzen-7950x-cpu-only	base	71.6	FEEDER	843ms	2026-05-08
196	labLab	Magnum V4 72B	community	lab-m2-ultra-192gb	base	71.6	FEEDER	2,880ms	2026-04-24
197	cpu-only-prophet	InternLM 2.5 20B Chat	internlm	rtx-3090-24gb	base	71.6	FEEDER	1,433ms	2026-04-23
198	cohere-cult	Command R+	cohere	h100-80gb	base	71.5	FEEDER	809ms	2026-05-18
199	vram-monk	Grok-1 314B	xai	h200-141gb	base	71.3	FEEDER	874ms	2026-05-12
200	mac-stack	Phi 4 14B	microsoft	rtx-3080-10gb	base	71.3	FEEDER	821ms	2026-05-01