ELO Rating90 models ranked

Chatbot Arena ELO Leaderboard 2026

Chatbot Arena ELO ranks models based on human preference in blind side-by-side conversations. It is the most widely cited real-world quality signal because it captures what humans actually prefer — not just benchmark overfitting.

Quick Answer

The best model on Chatbot Arena ELO in 2026 is Claude Opus 4 by Anthropic, scoring 1497 ELO. Runner-up: Claude Sonnet 4 (1473).

Provider

90 / 90 models

#	Model	Provider	Score	Percentile
🥇	Claude Opus 4	Anthropic	1497ELO	99th
🥈	Claude Sonnet 4	Anthropic	1473ELO	98th
🥉	Gemini 2.5 Pro	Google	1445ELO	97th
4	Claude Haiku 4	Anthropic	1415ELO	96th
5	DeepSeek R1	DeepSeek	1398ELO	94th
6	Qwen 2.5 Max	Alibaba	1374ELO	93th
7	Gemini 2.0 Flash	Google	1360ELO	92th
8	DeepSeek V3	DeepSeek	1358ELO	91th
9	o3-mini	OpenAI	1348ELO	90th
10	o3	OpenAI	1340ELO	89th
11	o1	OpenAI	1310ELO	88th
12	Qwen 3 235B MoE	Alibaba	1310ELO	87th
13	Gemini Experimental 1206	Google	1300ELO	86th
14	GPT-4.5	OpenAI	1290ELO	84th
15	DeepSeek R1 (Groq)	Groq	1290ELO	83th
16	Llama 4 Maverick	Meta	1290ELO	82th
17	DeepSeek R1 (Together)	Together AI	1290ELO	81th
18	Grok 3	xAI	1285ELO	80th
19	Gemini 2.0 Flash Thinking	Google	1280ELO	79th
20	Claude 3.5 Sonnet	Anthropic	1270ELO	78th
21	Gemini 2.5 Flash	Google	1270ELO	77th
22	o1-mini	OpenAI	1270ELO	76th
23	ChatGPT-4o Latest	OpenAI	1265ELO	74th
24	o4-mini	OpenAI	1260ELO	73th
25	QwQ 32B	Alibaba	1260ELO	72th
26	GPT-4o (Aug 2024)	OpenAI	1255ELO	71th
27	DeepSeek R1 Distill Llama 70B	DeepSeek	1250ELO	70th
28	Llama 4 Scout	Meta	1250ELO	69th
29	Mistral Large	Mistral	1245ELO	68th
30	Command A	Cohere	1240ELO	67th
31	DeepSeek R1 Distill Qwen 32B	DeepSeek	1240ELO	66th
32	Llama 3.1 405B (Fireworks)	Fireworks AI	1240ELO	64th
33	GPT-4 Turbo	OpenAI	1240ELO	63th
34	Grok 2	xAI	1240ELO	62th
35	Llama 3.1 405B	Meta	1240ELO	61th
36	Sonar Reasoning	Perplexity	1240ELO	60th
37	Llama 3.1 405B (Together)	Together AI	1240ELO	59th
38	Gemini 1.5 Pro	Google	1230ELO	58th
39	Grok 2 Vision	xAI	1230ELO	57th
40	Pixtral Large	Mistral AI	1230ELO	56th
41	Qwen 2.5 72B	Alibaba	1230ELO	54th
42	Qwen 2.5 72B (Together)	Together AI	1230ELO	53th
43	Amazon Nova Pro	Amazon	1220ELO	52th
44	Claude 3.5 Haiku	Anthropic	1220ELO	51th
45	Llama 3.3 70B (Fireworks)	Fireworks AI	1220ELO	50th
46	Llama 3.3 70B (Groq)	Groq	1220ELO	49th
47	Llama 3.3 70B	Meta	1220ELO	48th
48	Mistral Medium 3	Mistral AI	1220ELO	47th
49	Llama 3.3 70B (Together)	Together AI	1220ELO	46th
50	Llama 3.2 90B Vision	Meta	1210ELO	44th
51	Command R+	Cohere	1200ELO	43th
52	DeepSeek V2.5	DeepSeek	1200ELO	42th
53	Mixtral 8x22B (Fireworks)	Fireworks AI	1200ELO	41th
54	Gemini 2.0 Flash Lite	Google	1200ELO	40th
55	GPT-4 1	OpenAI	1200ELO	39th
56	Sonar Pro	Perplexity	1200ELO	38th
57	WizardLM-2 8x22B	Microsoft	1200ELO	37th
58	Llama 3.1 70B	Meta	1195ELO	36th
59	Phi-3.5 MoE	Microsoft	1195ELO	34th
60	Gemini 1.5 Flash	Google	1190ELO	33th
61	Gemma 2 27B	Google	1190ELO	32th
62	Mistral Small	Mistral	1185ELO	31th
63	Yi-Large	01.AI	1185ELO	30th
64	GPT-4 1.5-mini	OpenAI	1180ELO	29th
65	Grok 3-mini	xAI	1175ELO	28th
66	Amazon Nova Lite	Amazon	1170ELO	27th
67	Gemma 2 9B (Groq)	Groq	1170ELO	26th
68	Phi-3 Medium	Microsoft	1170ELO	24th
69	Yi-Lightning	01.AI	1165ELO	23th
70	GPT-4o	OpenAI	1162ELO	22th
71	Gemma 2 9B	Google	1160ELO	21th
72	Mixtral 8x7B (Groq)	Groq	1160ELO	20th
73	Llama 3.2 11B Vision	Meta	1160ELO	19th
74	Phi-3.5 Mini	Microsoft	1160ELO	18th
75	Qwen 2.5 7B	Alibaba	1160ELO	17th
76	Sonar	Perplexity	1160ELO	16th
77	InternLM 2.5 20B	Shanghai AI Lab	1155ELO	14th
78	Gemini 1.5 Flash 8B	Google	1150ELO	13th
79	GPT-4 1.5-nano	OpenAI	1150ELO	12th
80	Phi-4	Microsoft	1150ELO	11th
81	Command R	Cohere	1140ELO	10th
82	Mistral Nemo 12B	Mistral AI	1140ELO	9th
83	Amazon Nova Micro	Amazon	1130ELO	8th
84	Command R7B	Cohere	1120ELO	7th
85	GPT-3.5 Turbo	OpenAI	1120ELO	6th
86	Llama 3.1 8B (Groq)	Groq	1120ELO	4th
87	Llama 3.1 8B	Meta	1120ELO	3th
88	Mistral 7B	Mistral AI	1100ELO	2th
89	Mistral 7B (Together)	Together AI	1100ELO	1th
90	GPT-4o Mini	OpenAI	1098ELO	0th

What Chatbot Arena ELO Tests

Human preference across open-ended conversations. Models compete head-to-head; wins and losses update the ELO score. Higher ELO = humans prefer this model's output.

Score Range

1100–1400+ (average ~1200)

Source

LMSYS Chatbot Arena ↗

Other Benchmarks

Coding ELO Reasoning ELO HumanEval MMLU MATH GPQA

Compare models side-by-side

Full spec comparison — pricing, context window, and all benchmarks.

Compare Models →