LLM Leaderboard - Open WebUI

NOTICE

Open WebUI Community is currently undergoing a major revamp to improve user experience and performance. Expected completion by year-end! ✨

Leaderboard

315

RK	Model	Rating	Won	Lost
1	askleion-test	1180	100.0% 18	0.0% 0
2	llama3.2:3b-instruct-fp16	1171	64.7% 55	35.3% 30
3	anthropic.claude-3-haiku-20240307	1166	63.9% 85	36.1% 48
4	deepseek-coder-v2:16b-lite-instruct-q8_0	1161	93.8% 15	6.3% 1
5	hf.co/theprint/VanRossum-Qwen2.5-Coder-3B:Q8_0	1160	76.9% 20	23.1% 6
6	llama-3.2-90b-text-preview	1157	54.9% 50	45.1% 41
7	gpt-4o	1152	61.4% 35	38.6% 22
8	gemma2:9b-instruct-q5_K_M	1147	55.0% 33	45.0% 27
9	gpt-4o-mini	1145	63.7% 135	36.3% 77
10	ReWiz-Llama-3.2-3B.Q8_0.gguf:latest	1135	66.7% 28	33.3% 14
11	llama3.1:8b-instruct-q8_0	1133	62.2% 56	37.8% 34
12	llama3.1:8b-instruct-q5_K_M	1132	68.2% 30	31.8% 14
13	gemma2:2b	1125	78.9% 15	21.1% 4
14	grok-beta	1120	63.7% 51	36.3% 29
15	marco-o1:latest	1117	61.3% 19	38.7% 12
16	smollm2-1.7b-instruct	1115	75.0% 15	25.0% 5
17	mistralai/mistral-large-2411	1111	100.0% 7	0.0% 0
18	nemotron-mini:4b-instruct-fp16	1111	48.6% 35	51.4% 37
19	Vo.claude-3-5-sonnet-20240620	1102	81.8% 9	18.2% 2
20	openrouter-.google/gemini-pro-1.5	1101	59.0% 23	41.0% 16
21	closex/neuraldaredevil-8b-abliterated:Q6_K	1099	70.0% 28	30.0% 12
22	google/palm-2-codechat-bison	1096	100.0% 6	0.0% 0
23	Vo.claude-3-opus-20240229	1092	81.8% 9	18.2% 2
24	Vo.gemini-1.5-pro-latest	1083	81.8% 9	18.2% 2
25	gemini-exp-1121	1082	100.0% 5	0.0% 0
26	qwen2.5:14b-instruct-q3_K_S	1079	57.9% 22	42.1% 16
27	llama3.2:3b-instruct-q8_0	1075	65.0% 65	35.0% 35
28	chatgpt-4o-latest	1069	53.5% 38	46.5% 33
29	Boptruth-NeuralMonarch-7B-unsloth.Q6_K.gguf:latest	1068	56.5% 13	43.5% 10
30	x-ai/grok-beta	1068	85.7% 6	14.3% 1
31	llama3:latest	1067	64.3% 9	35.7% 5
32	gpt-4-turbo	1066	100.0% 4	0.0% 0
33	ReWiz-7B.Q4_K_S.gguf:latest	1058	62.2% 28	37.8% 17
34	mistral-nemo:12b-instruct-2407-q3_K_M	1056	59.4% 41	40.6% 28
35	llama3.1:8b-instruct-fp16	1056	83.3% 5	16.7% 1
36	llama3.1-latest	1055	83.3% 5	16.7% 1
37	qwen2.5-coder:latest	1050	58.8% 10	41.2% 7
38	grok-vision-beta	1050	100.0% 3	0.0% 0
39	yi-lightning	1048	64.0% 16	36.0% 9
40	claude-3-haiku-with-system-prompt	1048	50.0% 3	50.0% 3
41	gemma-7b-it	1046	80.0% 4	20.0% 1
42	misty	1046	100.0% 3	0.0% 0
43	mistralclaudefree20b-clone	1046	100.0% 3	0.0% 0
44	mistral:7b	1043	80.0% 4	20.0% 1
45	askleion-v1-qwen-25-7b	1042	100.0% 4	0.0% 0
46	anthropic/claude-3.5-sonnet	1042	66.7% 6	33.3% 3
47	gemini-exp-1114	1040	80.0% 4	20.0% 1
48	openai/gpt-4o	1037	66.7% 6	33.3% 3
49	askleion-v1-gemma9b	1036	66.7% 16	33.3% 8
50	Llama-3.1-Nemotron-70B-Instruct:latest	1036	80.0% 4	20.0% 1
51	mistral-nemo:latest	1035	51.0% 26	49.0% 25
52	Qwen/Qwen2.5-72B-Instruct	1034	100.0% 2	0.0% 0
53	ReWiz-Nemo-12B-Instruct-GGUF.Q4_K_M.gguf:latest	1034	51.5% 17	48.5% 16
54	vanilj/llama3.1-70b-iquants:IQ4_XS	1034	75.0% 3	25.0% 1
55	claude-3-5-sonnet-20241022	1033	100.0% 2	0.0% 0
56	starcoder2:3b	1033	100.0% 2	0.0% 0
57	ollama.com/library/medllama2:latest	1032	100.0% 2	0.0% 0
58	ollama.com/library/llama2-uncensored:7b	1032	100.0% 2	0.0% 0
59	Qwen/Qwen2.5-72B-Instruct-128K	1032	75.0% 3	25.0% 1
60	Qwen/Qwen2-7B-Instruct	1032	100.0% 2	0.0% 0
61	llama3.2-vision:latest	1031	75.0% 3	25.0% 1
62	vanessa	1031	100.0% 2	0.0% 0
63	hermes3:latest	1029	75.0% 3	25.0% 1
64	mistral-small:latest	1029	53.3% 8	46.7% 7
65	llama3.2:3b	1027	60.0% 9	40.0% 6
66	llama3:instruct	1022	100.0% 1	0.0% 0
67	anthropic.claude-3-5-sonnet-20240620	1021	100.0% 1	0.0% 0
68	hf.co/bartowski/Mistral-Small-Instruct-2409-GGUF:IQ3_M	1020	60.0% 6	40.0% 4
69	mistral-nemo:12b-instruct-2407-q5_K_M	1020	60.0% 9	40.0% 6
70	qwen2.5:32b	1019	55.6% 5	44.4% 4
71	argon	1018	48.8% 20	51.2% 21
72	llama3-uncensored:latest	1017	100.0% 1	0.0% 0
73	sonnet	1016	100.0% 1	0.0% 0
74	anthropic.claude-3-5-sonnet-latest	1016	100.0% 1	0.0% 0
75	Qwen/QwQ-32B-Preview	1016	100.0% 1	0.0% 0
76	doubao-pro-128k	1016	100.0% 1	0.0% 0
77	claude-3-5-sonnet-20240620	1016	66.7% 2	33.3% 1
78	reflection	1016	100.0% 1	0.0% 0
79	gpt-4-turbo-2024-04-09	1016	100.0% 1	0.0% 0
80	hf.co/TheBloke/dolphin-2.6-mistral-7B-dpo-laser-GGUF:Q5_K_M	1016	100.0% 1	0.0% 0
81	llama3.2:70b-text-fp16	1016	100.0% 1	0.0% 0
82	mythomax-l2-13b	1016	100.0% 1	0.0% 0
83	playground-v2.5	1016	100.0% 1	0.0% 0
84	blackboxai-pro	1016	100.0% 1	0.0% 0
85	wizardlm-2-8x22b	1016	100.0% 1	0.0% 0
86	anthropic/claude-3.5-sonnet:beta	1016	100.0% 1	0.0% 0
87	coders	1016	66.7% 2	33.3% 1
88	hermes3:8b-llama3.1-q8_0	1016	100.0% 1	0.0% 0
89	test	1016	100.0% 1	0.0% 0
90	llama-3.2-90b-vision-preview	1014	41.4% 12	58.6% 17
91	gemini-1.5-flash-exp-0827	1013	100.0% 1	0.0% 0
92	llama3.1:latest	1010	55.4% 62	44.6% 50
93	small-models	1009	50.0% 3	50.0% 3
94	gpt-4o-mini-2024-07-18	1008	50.0% 7	50.0% 7
95	deal-reg-generator	1007	45.5% 10	54.5% 12
96	llama-3.1-8b-instruct:latest	1005	50.0% 4	50.0% 4
97	mistral_small_obliterated_22b:latest	1002	50.0% 2	50.0% 2
98	qwen2.5:7b	1001	45.1% 41	54.9% 50
99	mental-health-assistant	1001	50.0% 1	50.0% 1
100	chatgpt-4-uncensored:latest	1000	50.0% 2	50.0% 2
101	shirka-ict-o1	1000	50.0% 1	50.0% 1
102	deepseek-coder-v2:latest	1000	50.0% 1	50.0% 1
103	llama-3.2-11b-vision-preview	1000	50.0% 2	50.0% 2
104	ollama.com/library/meditron:7b	1000	50.0% 1	50.0% 1
105	gemini-1.5-pro-002	1000	50.0% 1	50.0% 1
106	visual_tree_of_thoughts.mcts-nomic-embed-text:latest	1000	50.0% 1	50.0% 1
107	sarah-lovely-caring-girlfriend:latest	1000	50.0% 3	50.0% 3
108	starcoder2:15b	1000	50.0% 5	50.0% 5
109	qwen2.5:72b-instruct-q4_K_S	1000	50.0% 1	50.0% 1
110	CognitiveComputations/dolphin-mistral-nemo:12b-v2.9.3-Q5_K_M	1000	50.0% 2	50.0% 2
111	testout-helper	1000	50.0% 1	50.0% 1
112	RasLike-Qwen2.5-3B.Q4_K_M.gguf:latest	999	50.0% 1	50.0% 1
113	fever-dreams	999	50.0% 1	50.0% 1
114	original-models	998	50.0% 1	50.0% 1
115	gemma2:27b	996	50.0% 2	50.0% 2
116	qwen2.5:latest	995	50.0% 2	50.0% 2
117	hf.co/theprint/RuDolph-Hermes-7B-Q6_K-GGUF:latest	995	43.8% 14	56.3% 18
118	llama3.1:70b	992	40.0% 2	60.0% 3
119	llama3.2-vision:11b	990	44.4% 4	55.6% 5
120	atsi-ai	990	0.0% 0	100.0% 1
121	arena	989	40.0% 2	60.0% 3
122	llama3.2:latest	988	50.9% 29	49.1% 28
123	llama3.2:3b-instruct-q5_K_M	988	42.9% 3	57.1% 4
124	llama3-70b-8192	988	57.1% 52	42.9% 39
125	Vo.gpt-4o	987	40.0% 2	60.0% 3
126	arena-random-model	987	33.3% 1	66.7% 2
127	Qwen/Qwen2.5-Math-72B-Instruct	987	0.0% 0	100.0% 1
128	llama-3.2-3b-preview	987	33.3% 1	66.7% 2
129	Vo.flux-pro-max	986	40.0% 2	60.0% 3
130	hank	986	0.0% 0	100.0% 1
131	openrouter-.google/gemini-exp-1121:free	986	0.0% 0	100.0% 1
132	multi-agent:latest	985	0.0% 0	100.0% 1
133	intui	985	0.0% 0	100.0% 1
134	gpt-4o-2024-05-13	984	0.0% 0	100.0% 1
135	Vo.gemini-ultra	984	40.0% 2	60.0% 3
136	codellama:latest	984	0.0% 0	100.0% 1
137	haiku	984	0.0% 0	100.0% 1
138	o1-preview	984	0.0% 0	100.0% 1
139	ERNIE-Speed-128K	984	0.0% 0	100.0% 1
140	leon	984	0.0% 0	100.0% 1
141	hf.co/TheBloke/dolphin-2.6-mistral-7B-dpo-laser-GGUF:Q6_K	984	0.0% 0	100.0% 1
142	gemma2-9b-it	984	0.0% 0	100.0% 1
143	cohere/command-r-03-2024	984	0.0% 0	100.0% 1
144	mid-large-perf	984	0.0% 0	100.0% 1
145	over	984	0.0% 0	100.0% 1
146	meta-llama/llama-3.1-405b-instruct:free	984	0.0% 0	100.0% 1
147	anthropic/claude-1.2	984	0.0% 0	100.0% 1
148	nousresearch/nous-hermes-2-mixtral-8x7b-dpo	984	0.0% 0	100.0% 1
149	general	984	0.0% 0	100.0% 1
150	microsoft/wizardlm-2-8x22b	984	0.0% 0	100.0% 1
151	openai/gpt-4o-2024-08-06	984	0.0% 0	100.0% 1
152	google/palm-2-chat-bison	984	0.0% 0	100.0% 1
153	test2	984	0.0% 0	100.0% 1
154	anamnesetest	983	42.9% 3	57.1% 4
155	hf.co/theprint/Llama-3.2-3B-VanRossum:Q8_0	983	48.6% 18	51.4% 19
156	internclaudefree20b	983	0.0% 0	100.0% 1
157	joey	983	33.3% 1	66.7% 2
158	ministral-8b-latest	982	50.0% 5	50.0% 5
159	internlm2:20b	981	42.9% 3	57.1% 4
160	lamma-resumos-de-vdeo	980	48.1% 13	51.9% 14
161	qwen2.5:14b-instruct-q4_K_S	976	40.0% 8	60.0% 12
162	CleverBoi-Llama-3.2-3B-Instruct.Q8_0.gguf:latest	974	49.1% 27	50.9% 28
163	home-turf	973	39.0% 16	61.0% 25
164	CognitiveComputations/dolphin-phi-3:medium-v2.9.2-q5_k_m	973	0.0% 0	100.0% 2
165	hf.co/theprint/CleverBoi-Llama-3.1-8B-Instruct:Q5_K_M	972	37.5% 3	62.5% 5
166	glm-4-plus	971	0.0% 0	100.0% 2
167	deepseek-coder:6.7b-base	971	25.0% 1	75.0% 3
168	WorldBuilder-7B-GGUF.Q5_K_M.gguf:latest	971	44.4% 8	55.6% 10
169	llama3.1:8b	970	25.0% 1	75.0% 3
170	qwen2.5:72b-instruct-q4_0	970	0.0% 0	100.0% 2
171	openhermes:7b-mistral-v2-q5_K_M	968	44.8% 13	55.2% 16
172	THUDM/glm-4-9b-chat	968	0.0% 0	100.0% 2
173	llama-3.2-3b-instruct	967	25.0% 1	75.0% 3
174	gemini-1.5-pro-exp-0827	966	0.0% 0	100.0% 2
175	llama-3.1-70b-versatile	966	20.0% 1	80.0% 4
176	mixtral-8x7b-32768	965	39.0% 30	61.0% 47
177	llama3.1:8b-instruct-q4_0	965	0.0% 0	100.0% 2
178	llava:latest	965	37.5% 3	62.5% 5
179	CleverBoi-Nemo-12B-v2.Q4_K_S.gguf:latest	963	45.2% 14	54.8% 17
180	gpt-4o-2024-08-06	961	28.6% 2	71.4% 5
181	hf.co/theprint/ReWiz-Qwen-2.5-14B:Q4_K_S	959	33.3% 2	66.7% 4
182	doubao-pro-4k	957	0.0% 0	100.0% 3
183	openrouter-.anthropic/claude-3.5-sonnet	956	45.2% 19	54.8% 23
184	askleion-v1-mistral-7bv03q4km	955	37.8% 17	62.2% 28
185	gemma2:latest	955	0.0% 0	100.0% 3
186	openrouter-.meta-llama/llama-3.1-405b-instruct	954	46.8% 22	53.2% 25
187	ollama.com/bengt0/em_german_leo_mistral:latest	953	0.0% 0	100.0% 3
188	gemma2:9b	952	43.1% 31	56.9% 41
189	llama3.2:1b	951	51.0% 26	49.0% 25
190	llama3.2-vision:90b	947	25.0% 2	75.0% 6
191	phi3:latest	947	28.6% 2	71.4% 5
192	google/gemini-exp-1114	944	33.3% 4	66.7% 8
193	doubao-pro-32k	943	0.0% 0	100.0% 4
194	llama-3.2-1b-preview	940	44.0% 11	56.0% 14
195	exclude	940	0.0% 0	100.0% 4
196	gpt-4	939	0.0% 0	100.0% 4
197	deepseek-coder-v2:16b-lite-instruct-q4_0	935	48.1% 26	51.9% 28
198	minicpm-v:latest	935	27.3% 12	72.7% 32
199	qwen2.5-coder-1.5b-instruct-mlx	932	35.0% 7	65.0% 13
200	hf.co/theprint/ReWiz-Llama-3.2-1B:latest	924	41.3% 19	58.7% 27
201	gemini-1.5-pro	924	0.0% 0	100.0% 5
202	mistral:latest	923	28.6% 4	71.4% 10
203	gemma2-2b	919	33.3% 8	66.7% 16
204	mistral:7b-instruct-q4_K_S	918	40.0% 16	60.0% 24
205	gemini-1.5-flash-002	917	11.1% 1	88.9% 8
206	askleion-v1-mistral-nemo	914	33.3% 8	66.7% 16
207	anthropic/claude-3-sonnet:beta	901	11.1% 1	88.9% 8
208	llama-3.1-8b-instant	900	33.9% 19	66.1% 37
209	deepseek-ai/DeepSeek-V2.5	897	9.1% 1	90.9% 10
210	granite3-dense:8b-instruct-q5_K_M	897	35.3% 18	64.7% 33
211	gpt-3.5-turbo	896	10.0% 1	90.0% 9
212	google/gemini-pro-1.5	896	0.0% 0	100.0% 7
213	deepseek-coder:latest	889	0.0% 0	100.0% 11
214	x/llama3.2-vision:latest	889	38.2% 13	61.8% 21
215	Vo.o1-preview	885	9.1% 1	90.9% 10
216	Vo.o1-mini	881	9.1% 1	90.9% 10
217	mistral-nemo:12b-instruct-2407-q8_0	881	50.0% 39	50.0% 39
218	ReWiz-Worldbuilder-7B-GGUF.Q5_K_M.gguf:latest	877	28.6% 10	71.4% 25
219	arena-model	874	39.6% 59	60.4% 90
220	llama3-8b-8192	874	24.2% 31	75.8% 97
221	nemotron-mini:latest	857	28.9% 11	71.1% 27
222	openrouter-.mistralai/mistral-large-2411	856	33.3% 10	66.7% 20
223	askleion-v1-phi35	855	32.1% 9	67.9% 19
224	Nerdish-Llama-3.1-8B.Q4_K_M.gguf:latest	848	18.2% 4	81.8% 18
225	codellama:13b	845	8.3% 1	91.7% 11
226	granite3-moe:3b-instruct-q6_K	842	26.1% 12	73.9% 34
227	granite3-dense:8b	837	18.8% 3	81.3% 13
-	-assistant	-	-	-
-	70b-models	-	-	-
-	ai-bot-expert-programmer	-	-	-
-	aia/dolphin-llama3.1:latest	-	-	-
-	aminadaven/dictalm2.0-instruct:q5_k_m	-	-	-
-	anamnesebot	-	-	-
-	anthropic.claude-3-sonnet-20240229	-	-	-
-	azure_openai	-	-	-
-	azure-admin-expert	-	-	-
-	cmdt-escalona	-	-	-
-	cmdt-escalona-o1-mini	-	-	-
-	code-companion:latest	-	-	-
-	codegemma:7b	-	-	-
-	codellama:7b	-	-	-
-	codestral-mamba-latest	-	-	-
-	cohere_dbscan	-	-	-
-	cohere.command-r-plus	-	-	-
-	cyberwald/llama-3.1-sauerkrautlm-8b-instruct:latest	-	-	-
-	ddg/claude-3-haiku	-	-	-
-	deepseek-chat	-	-	-
-	dolphin-llama3:8b-256k-v2.9-q6_K	-	-	-
-	dolphin-mistral:latest	-	-	-
-	dolphin-phi:2.7b	-	-	-
-	eva	-	-	-
-	excel-assistant	-	-	-
-	excelv2	-	-	-
-	exer/laser-dolphin-mixtral:2x7b-dpo-q6_K	-	-	-
-	finalend/llama-3.1-storm:8b-q6_K	-	-	-
-	funktion-test	-	-	-
-	gemini-pro	-	-	-
-	gemma:2b	-	-	-
-	glm-4	-	-	-
-	google_genai.gemini-exp-1121	-	-	-
-	gpt-3.5-turbo-0125	-	-	-
-	gpt-3.5-turbo-1106	-	-	-
-	gpt-3.5-turbo-16k	-	-	-
-	gpt-4-0613	-	-	-
-	granite3-moe:3b-instruct-q5_K_M	-	-	-
-	graveler	-	-	-
-	hf.co/LiuWoodsCode/Llama32Cyn:latest	-	-	-
-	image-analysis	-	-	-
-	it-norms-expert-germma27b	-	-	-
-	llama-3.1-405b	-	-	-
-	Llama-3.1-8B-Lexi-Uncensored.Q4_K_S:latest	-	-	-
-	llama-arena	-	-	-
-	llama-guard-3-8b	-	-	-
-	llama2-uncensored:latest	-	-	-
-	llama3.2-vision:11b-instruct-q8_0	-	-	-
-	llama3.2:3b-instruct-q6_K	-	-	-
-	llava:13b-v1.6-vicuna-q5_K_M	-	-	-
-	malyki-vision-v1	-	-	-
-	MalyKIv3:latest	-	-	-
-	marco-o1:7b-q4_K_M	-	-	-
-	meta-llama/llama-3.1-70b-instruct:free	-	-	-
-	ministral-3b-2410	-	-	-
-	mistral-large-latest	-	-	-
-	mistral-medium-2312	-	-	-
-	mistral-small-2402	-	-	-
-	nemotron-mini:4b	-	-	-
-	o1-mini	-	-	-
-	o1-mini-2024-09-12	-	-	-
-	o1-preview-2024-09-12	-	-	-
-	ollama.com/library/mistral-nemo:latest	-	-	-
-	openai/gpt-3.5-turbo-instruct	-	-	-
-	phi3:14b-medium-128k-instruct-q5_K_M	-	-	-
-	phi3.5:3.8b-mini-instruct-q5_K_M	-	-	-
-	phi3.5:3.8b-mini-instruct-q8_0	-	-	-
-	pixtral-12b-2409	-	-	-
-	professor-de-biologia-em-portugues:latest	-	-	-
-	Qwen/Qwen2.5-7B-Instruct	-	-	-
-	Qwen/Qwen2.5-Coder-32B-Instruct	-	-	-
-	qwen2-math:7b	-	-	-
-	qwen2:latest	-	-	-
-	qwen2.5-coder:1.5b	-	-	-
-	qwen2.5-coder:3b	-	-	-
-	qwen2.5-coder:7b	-	-	-
-	qwen2.5:3b	-	-	-
-	qwen2.5:72b	-	-	-
-	random	-	-	-
-	run_se	-	-	-
-	siliconflow_api_connection.Qwen/Qwen2-VL-72B-Instruct	-	-	-
-	socialnetwooky/llama3.2-abliterated:3b_q8_0	-	-	-
-	sroecker/sauerkrautlm-7b-hero:latest	-	-	-
-	stablelm2:12b-chat-q4_K_M	-	-	-
-	starcoder2:7b	-	-	-
-	tencent_hunyuanai.hunyuan-pro	-	-	-
-	undi95/remm-slerp-l2-13b	-	-	-
-	wizard-vicuna-uncensored:latest	-	-	-

ⓘ The evaluation leaderboard is based on the Elo rating system and is updated in real-time.

The leaderboard is currently in beta, and we may adjust the rating calculations as we refine the algorithm.

Feedback History

1360

Models	Result	Updated At
llama3.2:latest	Won	5 hours ago
gpt-4o-2024-05-13	Lost	7 days ago
chatgpt-4-uncensored:latest	Won	3 days ago
chatgpt-4-uncensored:latest	Won	3 days ago
chatgpt-4-uncensored:latest	Won	3 days ago
chatgpt-4-uncensored:latest	Lost	3 days ago
chatgpt-4-uncensored:latest	Lost	3 days ago
chatgpt-4-uncensored:latest	Won	3 days ago
chatgpt-4-uncensored:latest	Lost	3 days ago
chatgpt-4-uncensored:latest	Lost	3 days ago

Help us create the best community leaderboard by sharing your feedback history!

...