Text Generation Arena Leaderboard

Name: Text Generation Arena Leaderboard
Creator: DataLearner
License: https://creativecommons.org/licenses/by/4.0/

The latest AI text generation leaderboard based on LMArena anonymous user voting. Covers Elo scores, confidence intervals, and vote counts for leading language models.

Top Model

Claude Fable 5

Top Score

1,507

Model Count

385

Data version

2026年08月06日

Data source: LM Arena

About This Leaderboard

This leaderboard ranks the strongest AI models for text generation. Data comes from LMArena (formerly LMSYS Chatbot Arena), the world's largest crowdsourced AI evaluation platform. Users chat with two anonymous models side-by-side and vote for the better response — rankings are determined entirely by real user preferences, not lab benchmarks.

Methodology Overview

Blind testing: Users chat with two anonymous models and vote based on response quality, eliminating brand bias.

Elo scoring: Using the Bradley-Terry model (adapted from chess Elo ratings) to calculate each model's strength score from battle outcomes. Higher scores mean users more frequently prefer that model.

Broad scenario coverage: Testing spans coding, creative writing, math reasoning, Q&A, role-playing, and more.

DataLearner provides in-depth analysis on top of the raw data, linking leaderboard models to the DataLearner model database so you can quickly access model details, API pricing, benchmark scores, and more.

Origin:All China

Leaderboard snapshot month:

Ranking Table

Rank	Model	Score	95% CI	Votes	Organization	License
	Claude Fable 5Anthropic	1,507	+/-6	19,390	Anthropic	Proprietary
	Claude Opus 4.6 (thinking)Anthropic	1,505	+/-4	69,336	Anthropic	Proprietary
	Opus 4.7 (thinking)Anthropic	1,502	+/-4	57,018	Anthropic	Proprietary
4	muse-spark-1.2 (xHigh)Meta	1,498	+/-13	2,057	Meta	Proprietary
5	Claude Opus 4.6Anthropic	1,497	+/-3	73,158	Anthropic	Proprietary
6	Qwen3.8-Max阿里巴巴	1,497	+/-9	4,662	阿里巴巴	Proprietary
7	Opus 4.7Anthropic	1,493	+/-4	58,135	Anthropic	Proprietary
8	Claude Opus 5 (high)Anthropic	1,493	+/-6	14,902	Anthropic	Proprietary
9	Claude Opus 5 (max)Anthropic	1,488	+/-8	7,137	Anthropic	Proprietary
10	Muse SparkFacebook AI研究实验室	1,488	+/-6	13,476	Facebook AI研究实验室	Proprietary
11	Muse Spark 1.1Facebook AI研究实验室	1,487	+/-6	14,227	Facebook AI研究实验室	Proprietary
12	Gemini 3.1 Pro PreviewGoogle Deep Mind	1,487	+/-3	91,328	Google Deep Mind	Proprietary
13	Gemini 3 ProGoogle Deep Mind	1,486	+/-4	41,242	Google Deep Mind	Proprietary
14	Kimi K3 (max)Moonshot AI	1,485	+/-7	9,861	Moonshot AI	Kimi K3 license
15	Gemini 3.6 FlashGoogle Deep Mind	1,485	+/-6	10,968	Google Deep Mind	Proprietary
16	Claude Opus 4.8 (thinking)Anthropic	1,483	+/-5	37,546	Anthropic	Proprietary
17	GPT-5.5 (high)OpenAI	1,482	+/-4	52,142	OpenAI	Proprietary
18	gpt-5.6-sol-xhighOpenAI	1,482	+/-6	12,839	OpenAI	Proprietary
19	GPT-5.4 (high)OpenAI	1,477	+/-4	60,156	OpenAI	Proprietary
20	GPT-5.5OpenAI	1,477	+/-4	53,407	OpenAI	Proprietary
21	gemini-3.5-flash-highGoogle	1,476	+/-5	22,797	Google	Proprietary
22	GPT-5.2 Chat (0210)OpenAI	1,476	+/-4	34,020	OpenAI	Proprietary
23	Qwen3.7-Max-Preview阿里巴巴	1,475	+/-10	3,695	阿里巴巴	Proprietary
24	Grok 4.20 BetaxAI	1,474	+/-5	26,553	xAI	Proprietary
25	gemini-3.5-flash-mediumGoogle	1,474	+/-5	21,100	Google	Proprietary
26	GPT-5.5 InstantOpenAI	1,474	+/-5	25,642	OpenAI	Proprietary
27	Gemini 3.0 FlashGoogle Deep Mind	1,473	+/-4	30,625	Google Deep Mind	Proprietary
28	Claude Opus 4.8Anthropic	1,473	+/-5	38,131	Anthropic	Proprietary
29	Claude Opus 4 (thinking-32k)Anthropic	1,473	+/-4	36,960	Anthropic	Proprietary
30	Claude Sonnet 4.6Anthropic	1,472	+/-4	63,453	Anthropic	Proprietary
31	grok-4.20-beta-0309-reasoningxAI	1,472	+/-4	61,639	xAI	Proprietary
32	grok-4.20-multi-agent-beta-0309xAI	1,471	+/-4	60,322	xAI	Proprietary
33	glm-5.2-maxZ.ai	1,471	+/-5	24,250	Z.ai	MIT
34	Claude Opus 4Anthropic	1,469	+/-3	70,504	Anthropic	Proprietary
35	Grok 4.5xAI	1,468	+/-6	14,883	xAI	Proprietary
36	GLM 5.1智谱AI	1,468	+/-4	36,716	智谱AI	MIT
37	ERNIE-5.1-Preview百度	1,467	+/-5	36,820	百度	Proprietary
38	gpt-5.6-terra-xhighOpenAI	1,467	+/-6	13,275	OpenAI	Proprietary
39	mimo-v2.5-proXiaomi	1,467	+/-4	47,805	Xiaomi	MIT
40	Grok 4.1 ThinkingxAI	1,466	+/-3	65,044	xAI	Proprietary
41	Qwen3.5 Max Preview阿里巴巴	1,465	+/-5	21,274	阿里巴巴	Proprietary
42	GPT-5.4OpenAI	1,465	+/-4	63,097	OpenAI	Proprietary
43	Claude Sonnet 4.5 (high)Anthropic	1,463	+/-5	20,311	Anthropic	Proprietary
44	Kimi K2.6Moonshot AI	1,461	+/-5	37,236	Moonshot AI	Modified MIT
45	Qwen3.6-Max-Preview阿里巴巴	1,460	+/-8	5,146	阿里巴巴	Proprietary
46	Grok 4.1xAI	1,460	+/-3	67,246	xAI	Proprietary
47	Gemini 3.5 Flash-LiteGoogle Deep Mind	1,459	+/-6	10,847	Google Deep Mind	Proprietary
48	Gemini 3.0 Flash (minimal)Google Deep Mind	1,459	+/-3	85,546	Google Deep Mind	Proprietary
49	Qwen3.7-Plus阿里巴巴	1,458	+/-5	28,111	阿里巴巴	Proprietary
50	DeepSeek-V4-ProDeepSeek-AI	1,457	+/-4	51,266	DeepSeek-AI	MIT
51	GLM-5智谱AI	1,457	+/-4	27,591	智谱AI	MIT
52	DOLA Seed 2.0 Pro字节跳动Seed团队	1,456	+/-4	73,874	字节跳动Seed团队	Proprietary
53	Claude Sonnet 4.5 (thinking-32k)Anthropic	1,456	+/-3	81,888	Anthropic	Proprietary
54	deepseek-v4-pro-high-previewDeepSeek	1,456	+/-4	48,756	DeepSeek	MIT
55	Claude Sonnet 4.5Anthropic	1,455	+/-3	80,284	Anthropic	Proprietary
56	GPT-5.1 Pro (high)OpenAI	1,454	+/-4	40,680	OpenAI	Proprietary
57	Hy3腾讯AI实验室	1,453	+/-10	3,941	腾讯AI实验室	Apache 2.0
58	Gemma 4 31BDeepMind	1,451	+/-8	5,839	DeepMind	Apache 2.0
59	Kimi K2 ThinkingMoonshot AI	1,451	+/-3	68,179	Moonshot AI	Modified MIT
60	gpt-5.6-luna-xhighOpenAI	1,450	+/-6	13,651	OpenAI	Proprietary
61	Opus 4.1 (thinking-16k)Anthropic	1,449	+/-3	49,720	Anthropic	Proprietary
62	ERNIE 5.0 Preview (1203)百度	1,449	+/-7	9,727	百度	Proprietary
63	GPT-5.3 ChatOpenAI	1,449	+/-4	32,583	OpenAI	Proprietary
64	GPT-5.4 mini (high)OpenAI	1,448	+/-4	58,984	OpenAI	Proprietary
65	mimo-v2-proXiaomi	1,448	+/-5	24,211	Xiaomi	Proprietary
66	Opus 4.1Anthropic	1,447	+/-3	77,192	Anthropic	Proprietary
67	ERNIE 5.0 (0110)百度	1,447	+/-4	35,015	百度	Proprietary
68	Gemini 2.5 ProGoogle Deep Mind	1,446	+/-2	124,014	Google Deep Mind	Proprietary
69	GPT-4.5OpenAI	1,445	+/-6	14,547	OpenAI	Proprietary
70	MiniMax M3MiniMaxAI	1,445	+/-5	34,343	MiniMaxAI	MiniMax Community License
71	Qwen 3.6 Plus Preview阿里巴巴	1,443	+/-4	45,033	阿里巴巴	Proprietary
72	GPT-4o(2025-03-27)OpenAI	1,443	+/-3	82,353	OpenAI	Proprietary
73	Qwen3.5-397B-A17B阿里巴巴	1,442	+/-4	63,719	阿里巴巴	Apache 2.0
74	GLM-4.7智谱AI	1,442	+/-6	12,077	智谱AI	MIT
75	Grok 4.3 BetaxAI	1,442	+/-4	53,234	xAI	Proprietary
76	InklingThinking Machines Lab	1,442	+/-6	12,086	Thinking Machines Lab	Apache 2.0
77	GPT-5.1OpenAI	1,439	+/-4	43,306	OpenAI	Proprietary
78	Gemma 4 26B A4BDeepMind	1,438	+/-8	5,755	DeepMind	Apache 2.0
79	deepseek-v4-flash-high-previewDeepSeek	1,438	+/-4	48,316	DeepSeek	MIT
80	GPT-5.2 Pro (high)OpenAI	1,438	+/-4	47,621	OpenAI	Proprietary
81	DeepSeek-V4-FlashDeepSeek-AI	1,436	+/-4	48,561	DeepSeek-AI	MIT
82	GPT-5.2OpenAI	1,435	+/-3	78,662	OpenAI	Proprietary
83	longcat-flash-chat-2602-expMeituan	1,435	+/-5	27,706	Meituan	Proprietary
84	Qwen3 Max (Preview)阿里巴巴	1,435	+/-5	27,670	阿里巴巴	Proprietary
85	mimo-v2.5Xiaomi	1,434	+/-4	44,200	Xiaomi	MIT
86	GPT-5-Pro (high)OpenAI	1,434	+/-5	31,877	OpenAI	Proprietary
87	GLM-5V-Turbo智谱AI	1,433	+/-7	9,288	智谱AI	Proprietary
88	Gemini 3.1 Flash-LiteGoogle Deep Mind	1,432	+/-4	60,041	Google Deep Mind	Proprietary
89	Kimi K2.5 InstantMoonshot AI	1,431	+/-7	8,138	Moonshot AI	Modified MIT
90	Grok 4.1 Fast (fast-reasoning)xAI	1,431	+/-3	56,402	xAI	Proprietary
91	OpenAI o3OpenAI	1,431	+/-4	59,661	OpenAI	Proprietary
92	mimo-v2-omniXiaomi	1,430	+/-6	19,216	Xiaomi	Proprietary
93	Kimi K2 Thinking (thinking-turbo)Moonshot AI	1,430	+/-3	61,677	Moonshot AI	Modified MIT
94	Mistral Medium 3.5MistralAI	1,427	+/-7	10,887	MistralAI	Modified MIT
95	GPT-5.2 Chat (0210)OpenAI	1,427	+/-4	31,517	OpenAI	Proprietary
96	Nemotron 3 UltraNVIDIA	1,426	+/-7	10,564	NVIDIA	OpenMDW-1.1
97	amazon-nova-experimental-chat-26-02-10Amazon	1,426	+/-10	3,392	Amazon	Proprietary
98	DeepSeek V3.2DeepSeek-AI	1,425	+/-4	46,999	DeepSeek-AI	MIT
99	GLM-4.6智谱AI	1,425	+/-4	35,589	智谱AI	MIT
100	DeepSeek V3.2-Exp (thinking)DeepSeek-AI	1,425	+/-7	9,051	DeepSeek-AI	MIT
101	Claude Opus 4 (thinking-16k)Anthropic	1,425	+/-4	36,832	Anthropic	Proprietary
102	qwen3-max-2025-09-23Alibaba	1,424	+/-6	9,138	Alibaba	Proprietary
103	Qwen3-235B-A22B-2507阿里巴巴	1,423	+/-3	96,721	阿里巴巴	Apache 2.0
104	DeepSeek V3.2-Exp (thinking)DeepSeek-AI	1,423	+/-4	40,832	DeepSeek-AI	MIT
105	DeepSeek V3.2-ExpDeepSeek-AI	1,423	+/-6	11,902	DeepSeek-AI	MIT
106	DeepSeek-R1-0528DeepSeek-AI	1,422	+/-6	18,422	DeepSeek-AI	MIT
107	Grok 4 FastxAI	1,421	+/-8	6,795	xAI	Proprietary
108	ERNIE 5.0百度	1,419	+/-9	4,702	百度	Proprietary
109	Kimi K2 0905Moonshot AI	1,418	+/-6	11,756	Moonshot AI	Modified MIT
110	Kimi K2Moonshot AI	1,418	+/-5	27,589	Moonshot AI	Modified MIT
111	DeepSeek-V3.1DeepSeek-AI	1,418	+/-6	14,942	DeepSeek-AI	MIT
112	DeepSeek-V3.1 Terminus (thinking)DeepSeek-AI	1,417	+/-10	3,454	DeepSeek-AI	MIT
113	Qwen3.5-122B-A10B阿里巴巴	1,417	+/-4	28,208	阿里巴巴	Apache 2.0
114	DeepSeek-V3.1 (thinking)DeepSeek-AI	1,417	+/-7	11,715	DeepSeek-AI	MIT
115	MiniMax-M2.7MiniMaxAI	1,416	+/-4	55,513	MiniMaxAI	Modified MIT
116	amazon-nova-experimental-chat-26-01-10Amazon	1,415	+/-10	3,392	Amazon	Proprietary
117	Mistral Large 3MistralAI	1,415	+/-3	56,503	MistralAI	Apache 2.0
118	Qwen3-VL-235B-A22B-Instruct阿里巴巴	1,415	+/-6	11,483	阿里巴巴	Apache 2.0
119	DeepSeek-V3.1 TerminusDeepSeek-AI	1,415	+/-10	3,688	DeepSeek-AI	MIT
120	GPT-4.1OpenAI	1,414	+/-4	50,899	OpenAI	Proprietary
121	Claude Opus 4Anthropic	1,413	+/-4	44,134	Anthropic	Proprietary
122	Haiku 4.5Anthropic	1,412	+/-3	114,721	Anthropic	Proprietary
123	hunyuan-hy3-previewTencent	1,412	+/-8	6,555	Tencent	tencent-hunyuan-community
124	Grok 3xAI	1,411	+/-4	32,861	xAI	Proprietary
125	GLM-4.5智谱AI	1,411	+/-5	24,269	智谱AI	MIT
126	Gemini 2.5 FlashGoogle Deep Mind	1,410	+/-2	123,929	Google Deep Mind	Proprietary
127	Grok 4xAI	1,409	+/-4	41,304	xAI	Proprietary
128	Magistral-Medium-2506MistralAI	1,409	+/-3	93,390	MistralAI	Proprietary
129	Qwen3.5-27B阿里巴巴	1,408	+/-4	27,052	阿里巴巴	Apache 2.0
130	Gemini 2.5 Flash-Preview-09-2025Google Deep Mind	1,404	+/-4	32,849	Google Deep Mind	Proprietary
131	Grok 4 Fast (fast-reasoning)xAI	1,404	+/-5	18,688	xAI	Proprietary
132	qwen3-235b-a22b-no-thinkingAlibaba	1,403	+/-5	38,137	Alibaba	Apache 2.0
133	GPT-5.4 nano (high)OpenAI	1,403	+/-4	57,979	OpenAI	Proprietary
134	OpenAI o1OpenAI	1,402	+/-4	27,807	OpenAI	Proprietary
135	Qwen3-Next阿里巴巴	1,401	+/-5	22,846	阿里巴巴	Apache 2.0
136	longcat-flash-chatMeituan	1,401	+/-6	11,379	Meituan	MIT
137	Claude Sonnet 4 (thinking-32k)Anthropic	1,399	+/-4	35,044	Anthropic	Proprietary
138	qwen3-235b-a22b-thinking-2507Alibaba	1,399	+/-7	8,975	Alibaba	Apache 2.0
139	DeepSeek-R1DeepSeek-AI	1,398	+/-5	18,524	DeepSeek-AI	MIT
140	Step 3.5 FlashStepFunAI	1,397	+/-4	57,847	StepFunAI	Proprietary
141	DeepSeek-V3-0324DeepSeek-AI	1,396	+/-4	45,445	DeepSeek-AI	MIT
142	Qwen3-VL-235B-A22B-Instruct (thinking)阿里巴巴	1,395	+/-7	7,934	阿里巴巴	Apache 2.0
143	Qwen3.5-35B-A3B阿里巴巴	1,395	+/-4	28,864	阿里巴巴	Apache 2.0
144	hunyuan-vision-1.5-thinkingTencent	1,395	+/-12	2,214	Tencent	Proprietary
145	Step 3.5 FlashStepFunAI	1,394	+/-4	56,979	StepFunAI	Apache 2.0
146	amazon-nova-experimental-chat-12-10Amazon	1,394	+/-10	3,672	Amazon	Proprietary
147	mimo-v2-flash (non-thinking)Xiaomi	1,393	+/-4	46,248	Xiaomi	MIT
148	GPT-5-mini (high)OpenAI	1,390	+/-5	26,987	OpenAI	Proprietary
149	OpenAI o4 - miniOpenAI	1,390	+/-4	45,383	OpenAI	Proprietary
150	MiniMax M2.5MiniMaxAI	1,390	+/-4	40,688	MiniMaxAI	Modified MIT
151	Claude Sonnet 4Anthropic	1,389	+/-4	40,242	Anthropic	Proprietary
152	OpenAI o1OpenAI	1,389	+/-5	31,122	OpenAI	Proprietary
153	Claude3-Sonnet (thinking-32k)Anthropic	1,388	+/-4	38,785	Anthropic	Proprietary
154	Qwen3-Coder-480B-A35B阿里巴巴	1,388	+/-5	25,674	阿里巴巴	Apache 2.0
155	mimo-v2-flash (thinking)Xiaomi	1,387	+/-6	10,909	Xiaomi	MIT
156	mistral-medium-2505Mistral	1,387	+/-5	33,178	Mistral	Proprietary
157	Hunyuan-T1腾讯AI实验室	1,387	+/-9	4,695	腾讯AI实验室	Proprietary
158	M2.1MiniMaxAI	1,384	+/-5	17,057	MiniMaxAI	MIT
159	Qwen3-30B-A3B-2507阿里巴巴	1,383	+/-5	23,691	阿里巴巴	Apache 2.0
160	GPT-4.1 miniOpenAI	1,383	+/-4	39,277	OpenAI	Proprietary
161	hunyuan-turbos-20250416Tencent	1,382	+/-6	10,715	Tencent	Proprietary
162	Gemini 2.5 Flash-Lite-Preview-09-2025 (no-thinking)Google Deep Mind	1,380	+/-3	47,142	Google Deep Mind	Proprietary
163	trinity-large-preview Apache 2.0	1,379	+/-4	29,651	—	—
164	GLM-4.6V智谱AI	1,377	+/-11	2,797	智谱AI	MIT
165	Qwen3-235B-A22B阿里巴巴	1,375	+/-5	26,241	阿里巴巴	Apache 2.0
166	Gemini 2.5 Flash-Lite (thinking)Google Deep Mind	1,375	+/-5	32,839	Google Deep Mind	Proprietary
167	Qwen2.5-Max阿里巴巴	1,374	+/-4	32,590	阿里巴巴	Proprietary
168	Claude 3.5 SonnetAnthropic	1,373	+/-3	88,291	Anthropic	Proprietary
169	GLM-4.5-Air智谱AI	1,373	+/-4	31,040	智谱AI	MIT
170	Claude3-SonnetAnthropic	1,372	+/-4	43,140	Anthropic	Proprietary
171	Qwen3-Next (thinking)阿里巴巴	1,369	+/-6	13,661	阿里巴巴	Apache 2.0
172	trinity-large-thinking Apache 2.0	1,369	+/-5	28,771	—	—
173	GLM-4.7-Flash智谱AI	1,368	+/-6	11,678	智谱AI	MIT
174	amazon-nova-experimental-chat-11-10Amazon	1,366	+/-4	25,264	Amazon	Proprietary
175	Gemma 3 - 27B (IT)Google Deep Mind	1,366	+/-4	47,453	Google Deep Mind	Gemma
176	minimax-m1MiniMax	1,364	+/-4	35,117	MiniMax	Apache 2.0
177	OpenAI o3-mini (high)OpenAI	1,364	+/-5	18,589	OpenAI	Proprietary
178	OpenAI o3-mini (high)OpenAI	1,362	+/-5	16,938	OpenAI	Proprietary
179	nvidia-nemotron-3-super-120b-a12bNvidia	1,361	+/-7	7,484	Nvidia	NVIDIA Open Model
180	Gemini 2.0 Flash ExperimentalDeepMind	1,361	+/-4	43,718	DeepMind	Proprietary
181	DeepSeek-V3DeepSeek-AI	1,359	+/-5	21,770	DeepSeek-AI	DeepSeek
182	Mistral-Small-3.2MistralAI	1,358	+/-5	17,685	MistralAI	Apache 2.0
183	grok-3-mini-betaxAI	1,357	+/-5	22,672	xAI	Proprietary
184	intellect-3 MIT	1,356	+/-8	5,323	—	—
185	C4AI Command A (202503)CohereAI	1,354	+/-3	56,175	CohereAI	CC-BY-NC-4.0
186	Gemini 2.0 Flash-LiteDeepMind	1,354	+/-4	24,955	DeepMind	Proprietary
187	GLM-4.5V智谱AI	1,354	+/-8	4,953	智谱AI	MIT
188	GPT OSS 120BOpenAI	1,352	+/-4	30,594	OpenAI	Apache 2.0
189	Gemini 1.5 ProGoogle Deep Mind	1,351	+/-3	55,606	Google Deep Mind	Proprietary
190	amazon-nova-experimental-chat-10-20Amazon	1,349	+/-6	11,449	Amazon	Proprietary
191	hunyuan-turbos-20250226Tencent	1,349	+/-12	2,220	Tencent	Proprietary
192	Step3StepFunAI	1,349	+/-7	6,531	StepFunAI	Apache 2.0
193	OpenAI o3-miniOpenAI	1,348	+/-4	57,283	OpenAI	Proprietary
194	llama-3.1-nemotron-ultra-253b-v1Nvidia	1,348	+/-12	2,549	Nvidia	Nvidia Open Model
195	amazon-nova-experimental-chat-10-09Amazon	1,348	+/-11	2,823	Amazon	Proprietary
196	Qwen3-32B阿里巴巴	1,347	+/-9	3,926	阿里巴巴	Apache 2.0
197	mercury-2 InceptionAI	1,347	+/-11	3,099	AI	Proprietary
198	ling-flash-2.0 AntGroup	1,346	+/-7	6,993	Group	MIT
199	qwen-plus-0125Alibaba	1,346	+/-8	5,819	Alibaba	Proprietary
200	MiniMax M2MiniMaxAI	1,346	+/-8	6,859	MiniMaxAI	Apache 2.0
201	GPT-4oOpenAI	1,346	+/-3	112,881	OpenAI	Proprietary
202	nvidia-llama-3.3-nemotron-super-49b-v1.5Nvidia	1,343	+/-10	3,340	Nvidia	Nvidia Open
203	glm-4-plus-0111Zhipu	1,343	+/-8	5,760	Zhipu	Proprietary
204	Claude 3.5 SonnetAnthropic	1,343	+/-3	82,419	Anthropic	Proprietary
205	Gemma 3 - 12B (IT)Google Deep Mind	1,342	+/-10	3,829	Google Deep Mind	Gemma
206	hunyuan-turbo-0110Tencent	1,341	+/-12	2,290	Tencent	Proprietary
207	GPT-5-Nano (high)OpenAI	1,337	+/-7	8,254	OpenAI	Proprietary
208	OpenAI o1-miniOpenAI	1,337	+/-4	51,981	OpenAI	Proprietary
209	Nova 2 Lite亚马逊	1,337	+/-6	12,213	亚马逊	Proprietary
210	QwQ-32B阿里巴巴	1,336	+/-4	25,361	阿里巴巴	Apache 2.0
211	Grok 2xAI	1,336	+/-4	63,498	xAI	Proprietary
212	gemini-advanced-0514Google	1,336	+/-5	50,148	Google	Proprietary
213	GPT-4oOpenAI	1,335	+/-4	45,499	OpenAI	Proprietary
214	llama-3.1-405b-instruct-bf16Meta	1,335	+/-4	41,375	Meta	Llama 3.1 Community
215	step-2-16k-exp-202412StepFun	1,334	+/-9	4,833	StepFun	Proprietary
216	llama-3.1-405b-instruct-fp8Meta	1,333	+/-4	59,656	Meta	Llama 3.1 Community
217	olmo-3.1-32b-instructAi2	1,330	+/-6	12,195	Ai2	Apache 2.0
218	molmo-2-8bAi2	1,329	+/-21	800	Ai2	Apache 2.0
219	yi-lightning Proprietary	1,328	+/-5	27,332	—	—
220	llama-3.3-nemotron-49b-super-v1Nvidia	1,328	+/-12	2,218	Nvidia	Nvidia
221	Qwen3-30B-A3B阿里巴巴	1,327	+/-5	26,448	阿里巴巴	Apache 2.0
222	Llama 4 Maverick InstructFacebook AI研究实验室	1,327	+/-4	39,928	Facebook AI研究实验室	Llama 4
223	hunyuan-large-2025-02-10Tencent	1,326	+/-10	3,738	Tencent	Proprietary
224	gpt-4-turbo-2024-04-09OpenAI	1,324	+/-4	98,114	OpenAI	Proprietary
225	Claude 3.5 HaikuAnthropic	1,324	+/-3	69,899	Anthropic	Proprietary
226	Gemini 1.5 ProGoogle Deep Mind	1,324	+/-4	79,138	Google Deep Mind	Proprietary
227	deepseek-v2.5-1210DeepSeek	1,324	+/-8	6,795	DeepSeek	DeepSeek
228	Llama 4 Scout InstructFacebook AI研究实验室	1,323	+/-5	30,251	Facebook AI研究实验室	Llama
229	GPT-4.1 nanoOpenAI	1,322	+/-8	6,103	OpenAI	Proprietary
230	Claude3-OpusAnthropic	1,322	+/-3	194,909	Anthropic	Proprietary
231	ring-flash-2.0 AntGroup	1,321	+/-7	7,129	Group	MIT
232	step-1o-turbo-202506StepFun	1,320	+/-7	9,023	StepFun	Proprietary
233	glm-4-plusZhipu AI	1,319	+/-5	26,126	Zhipu AI	Proprietary
234	Llama3.3-70B-InstructFacebook AI研究实验室	1,318	+/-3	54,698	Facebook AI研究实验室	Llama-3.3
235	Gemma-3n-E4BGoogle Deep Mind	1,318	+/-5	22,553	Google Deep Mind	Gemma
236	qwen-max-0919Alibaba	1,318	+/-6	16,478	Alibaba	Qwen
237	GPT-4o miniOpenAI	1,318	+/-4	68,707	OpenAI	Proprietary
238	GPT OSS 20BOpenAI	1,317	+/-6	10,618	OpenAI	Apache 2.0
239	nvidia-nemotron-3-nano-30b-a3b-bf16Nvidia	1,315	+/-6	15,489	Nvidia	NVIDIA Open Model
240	qwen2.5-plus-1127Alibaba	1,315	+/-6	10,187	Alibaba	Proprietary
241	athene-v2-chat NexusFlow	1,314	+/-5	24,739	—	—
242	mistral-large-2407Mistral	1,314	+/-4	45,459	Mistral	Mistral Research
243	GPT-4OpenAI	1,313	+/-4	93,439	OpenAI	Proprietary
244	GPT-4OpenAI	1,312	+/-4	100,105	OpenAI	Proprietary
245	hunyuan-standard-2025-02-10Tencent	1,311	+/-10	3,904	Tencent	Proprietary
246	gemini-1.5-flash-002Google	1,309	+/-4	34,902	Google	Proprietary
247	grok-2-mini-2024-08-13xAI	1,309	+/-4	52,567	xAI	Proprietary
248	DeepSeek V2.5DeepSeek-AI	1,307	+/-5	24,572	DeepSeek-AI	DeepSeek
249	athene-70b-0725 CC-BY-NC-4.0	1,307	+/-6	19,621	—	—
250	mercury InceptionAI	1,306	+/-14	1,953	AI	Proprietary
251	granite-4.1-8bIBM	1,306	+/-10	3,995	IBM	Apache 2.0
252	olmo-3-32b-thinkAi2	1,305	+/-8	5,930	Ai2	Apache 2.0
253	mistral-large-2411Mistral	1,305	+/-4	28,073	Mistral	MRL
254	Magistral-Medium-2506MistralAI	1,304	+/-6	11,617	MistralAI	Proprietary
255	Gemma 3 - 4B (IT)Google Deep Mind	1,303	+/-9	4,171	Google Deep Mind	Gemma
256	Mistral-Small-3.1-24B-Instruct-2503MistralAI	1,303	+/-5	33,180	MistralAI	Apache 2.0
257	Qwen2.5-VL-72B-Instruct阿里巴巴	1,303	+/-4	39,406	阿里巴巴	Qwen
258	Llama3.1-70B-InstructFacebook AI研究实验室	1,299	+/-8	7,140	Facebook AI研究实验室	Llama 3.1
259	hunyuan-large-visionTencent	1,294	+/-9	5,362	Tencent	Proprietary
260	Llama3.1-70B-InstructFacebook AI研究实验室	1,293	+/-4	55,240	Facebook AI研究实验室	Llama 3.1 Community
261	amazon-nova-pro-v1.0Amazon	1,290	+/-5	24,745	Amazon	Proprietary
262	jamba-1.5-large Jamba Open	1,289	+/-7	8,662	—	—
263	gemma-2-27b-itGoogle	1,289	+/-3	75,754	Google	Gemma license
264	reka-core-20240904 Proprietary	1,288	+/-7	7,312	—	—
265	ibm-granite-h-smallIBM	1,287	+/-8	5,677	IBM	Apache 2.0
266	GPT-4OpenAI	1,287	+/-5	54,173	OpenAI	Proprietary
267	gemini-1.5-flash-001Google	1,286	+/-5	62,833	Google	Proprietary
268	llama-3.1-nemotron-51b-instructNvidia	1,286	+/-10	3,749	Nvidia	Llama 3.1
269	llama-3.1-tulu-3-70bAi2	1,286	+/-10	2,846	Ai2	Llama 3.1
270	olmo-3.1-32b-thinkAi2	1,285	+/-7	8,485	Ai2	Apache 2.0
271	Claude3-SonnetAnthropic	1,281	+/-4	109,284	Anthropic	Proprietary
272	gemma-2-9b-it-simpo MIT	1,280	+/-7	10,072	—	—
273	nemotron-4-340b-instructNvidia	1,277	+/-5	19,659	Nvidia	NVIDIA Open Model
274	Llama3-70B-InstructFacebook AI研究实验室	1,276	+/-4	156,876	Facebook AI研究实验室	Llama 3 Community
275	command-r-plus-08-2024Cohere	1,276	+/-7	9,866	Cohere	CC-BY-NC-4.0
276	GPT-4OpenAI	1,275	+/-4	88,723	OpenAI	Proprietary
277	Mistral Small 24B Instruct 2501MistralAI	1,274	+/-6	14,681	MistralAI	Apache 2.0
278	GLM4智谱AI	1,273	+/-7	9,788	智谱AI	Proprietary
279	reka-flash-20240904 Proprietary	1,272	+/-7	7,536	—	—
280	Qwen2.5-Coder-32B-Instruct阿里巴巴	1,271	+/-8	5,432	阿里巴巴	Apache 2.0
281	C4AI Aya Vision 32BCohereAI	1,267	+/-5	27,124	CohereAI	CC-BY-NC-4.0
282	gemma-2-9b-itGoogle	1,267	+/-4	54,611	Google	Gemma license
283	deepseek-coder-v2DeepSeek	1,265	+/-6	15,147	DeepSeek	DeepSeek License
284	Qwen2-72B-Instruct阿里巴巴	1,261	+/-5	37,325	阿里巴巴	Qianwen LICENSE
285	C4AI Command R+CohereAI	1,261	+/-4	77,554	CohereAI	CC-BY-NC-4.0
286	Claude3-HaikuAnthropic	1,261	+/-4	117,701	Anthropic	Proprietary
287	amazon-nova-lite-v1.0Amazon	1,260	+/-5	19,372	Amazon	Proprietary
288	gemini-1.5-flash-8b-001Google	1,259	+/-4	35,558	Google	Proprietary
289	Phi-4-reasoningMicrosoft Azure	1,256	+/-5	24,126	Microsoft Azure	MIT
290	olmo-2-0325-32b-instructAi2	1,251	+/-11	3,334	Ai2	Apache-2.0
291	command-r-08-2024Cohere	1,250	+/-7	10,140	Cohere	CC-BY-NC-4.0
292	mistral-large-2402Mistral	1,242	+/-5	62,436	Mistral	Proprietary
293	amazon-nova-micro-v1.0Amazon	1,241	+/-5	19,364	Amazon	Proprietary
294	jamba-1.5-mini Jamba Open	1,240	+/-7	8,858	—	—
295	ministral-8b-2410Mistral	1,237	+/-9	4,781	Mistral	MRL
296	gemini-pro-dev-apiGoogle	1,236	+/-7	18,354	Google	Proprietary
297	Qwen1.5-110B-Chat阿里巴巴	1,234	+/-6	26,195	阿里巴巴	Qianwen LICENSE
298	hunyuan-standard-256kTencent	1,233	+/-12	2,728	Tencent	Proprietary
299	reka-flash-21b-20240226-online Proprietary	1,233	+/-7	15,450	—	—
300	Qwen1.5-72B-Chat阿里巴巴	1,233	+/-5	39,302	阿里巴巴	Qianwen LICENSE
301	Mixtral-8x22B-Instruct-v0.1MistralAI	1,229	+/-5	51,416	MistralAI	Apache 2.0
302	reka-flash-21b-20240226 Proprietary	1,226	+/-6	24,806	—	—
303	command-rCohere	1,226	+/-5	54,036	Cohere	CC-BY-NC-4.0
304	gpt-3.5-turbo-0125OpenAI	1,225	+/-5	66,207	OpenAI	Proprietary
305	Llama3-8B-InstructFacebook AI研究实验室	1,223	+/-4	104,642	Facebook AI研究实验室	Llama 3 Community
306	C4AI Aya Vision 8BCohereAI	1,223	+/-7	9,818	CohereAI	CC-BY-NC-4.0
307	Gemini-proDeepMind	1,223	+/-12	6,390	DeepMind	Proprietary
308	mistral-mediumMistral	1,222	+/-5	34,550	Mistral	Proprietary
309	llama-3.1-tulu-3-8bAi2	1,221	+/-11	2,896	Ai2	Llama 3.1
310	Yi-1.5-34B零一万物	1,213	+/-5	24,146	零一万物	—
311	zephyr-orpo-141b-A35b-v0.1 Apache 2.0	1,212	+/-11	4,652	—	—
312	Llama3.1-8B-InstructFacebook AI研究实验室	1,211	+/-4	49,605	Facebook AI研究实验室	Llama 3.1 Community
313	Llama3.1-8B-InstructFacebook AI研究实验室	1,208	+/-11	3,090	Facebook AI研究实验室	Apache 2.0
314	qwen1.5-32b-chatAlibaba	1,203	+/-6	21,741	Alibaba	Qianwen LICENSE
315	gpt-3.5-turbo-1106OpenAI	1,203	+/-9	16,619	OpenAI	Proprietary
316	gemma-2-2b-itGoogle	1,200	+/-4	46,616	Google	Gemma license
317	Phi-3-medium 14B-previewMicrosoft Azure	1,197	+/-5	25,055	Microsoft Azure	MIT
318	mixtral-8x7b-instruct-v0.1Mistral	1,197	+/-4	73,503	Mistral	Apache 2.0
319	dbrx-instruct-preview DBRX LICENSE	1,195	+/-6	32,191	—	—
320	InternLM2-Base-20B上海人工智能实验室	1,191	+/-7	9,901	上海人工智能实验室	—
321	Qwen1.5-14B-Chat阿里巴巴	1,191	+/-7	17,839	阿里巴巴	Qianwen LICENSE
322	DeepSeek LLM 67B ChatDeepSeek-AI	1,184	+/-11	4,932	DeepSeek-AI	DeepSeek License
323	WizardLM-70B-V1.0WizardLM Team	1,184	+/-9	8,214	WizardLM Team	Llama 2 Community
324	Yi-34B零一万物	1,183	+/-7	15,483	零一万物	—
325	granite-3.0-8b-instructIBM	1,182	+/-9	6,638	IBM	Apache 2.0
326	openchat-3.5 Apache-2.0	1,182	+/-10	7,968	—	—
327	openchat-3.5-0106 Apache-2.0	1,182	+/-8	12,637	—	—
328	Gemma 1.1-7B-ITGoogle Research	1,182	+/-6	23,893	Google Research	Gemma license
329	snowflake-arctic-instruct Apache 2.0	1,179	+/-6	32,832	—	—
330	granite-3.1-2b-instructIBM	1,179	+/-11	3,188	IBM	Apache 2.0
331	LLaMA2 70BFacebook AI研究实验室	1,177	+/-10	6,535	Facebook AI研究实验室	—
332	openhermes-2.5-mistral-7b Apache-2.0	1,175	+/-10	5,006	—	—
333	Vicuna 33BLM-SYS	1,172	+/-6	22,479	LM-SYS	—
334	starling-lm-7b-beta Apache-2.0	1,171	+/-7	16,056	—	—
335	Phi-3-small 7BMicrosoft Azure	1,171	+/-6	17,766	Microsoft Azure	MIT
336	llama-2-70b-chatMeta	1,170	+/-5	38,492	Meta	Llama 2 Community
337	starling-lm-7b-alpha CC-BY-NC-4.0	1,167	+/-8	10,224	—	—
338	llama-3.2-3b-instructMeta	1,166	+/-8	7,936	Meta	Llama 3.2
339	nous-hermes-2-mixtral-8x7b-dpo Apache-2.0	1,164	+/-12	3,777	—	—
340	Qwen3-VL-2B阿里巴巴	1,156	+/-8	6,837	阿里巴巴	Apache 2.0
341	QwQ-32B-Preview阿里巴巴	1,155	+/-11	3,231	阿里巴巴	Apache 2.0
342	llama2-70b-steerlm-chatNvidia	1,154	+/-13	3,585	Nvidia	Llama 2 Community
343	solar-10.7b-instruct-v1.0 CC-BY-NC-4.0	1,152	+/-13	4,155	—	—
344	dolphin-2.2.1-mistral-7b Apache-2.0	1,152	+/-15	1,679	—	—
345	mpt-30b-chat CC-BY-NC-SA-4.0	1,150	+/-12	2,572	—	—
346	wizardlm-13bMicrosoft	1,149	+/-9	7,044	Microsoft	Llama 2 Community
347	Mistral-7B-Instruct-v0.2MistralAI	1,149	+/-7	19,402	MistralAI	Apache-2.0
348	falcon-180b-chat Falcon-180B TII License	1,147	+/-17	1,295	—	—
349	Qwen1.5-7B-Chat阿里巴巴	1,143	+/-10	4,737	阿里巴巴	Qianwen LICENSE
350	Phi-3-mini 3.8BMicrosoft Azure	1,143	+/-6	12,297	Microsoft Azure	MIT
351	Baichuan2-13B-Chat百川智能	1,141	+/-7	19,174	百川智能	Llama 2 Community
352	vicuna-13b Llama 2 Community	1,141	+/-7	19,367	—	—
353	Qwen-14B-Chat阿里巴巴	1,139	+/-11	4,964	阿里巴巴	Qianwen LICENSE
354	PaLM 2Google Research	1,138	+/-9	8,554	Google Research	Proprietary
355	Gemma 7B - ItGoogle Research	1,137	+/-9	8,925	Google Research	Gemma license
356	CodeLLaMA-34BFacebook AI研究实验室	1,136	+/-9	7,366	Facebook AI研究实验室	Llama 2 Community
357	zephyr-7b-beta MIT	1,130	+/-9	11,118	—	—
358	Phi-3-mini 3.8BMicrosoft Azure	1,129	+/-7	20,685	Microsoft Azure	MIT
359	Phi-3-mini 3.8BMicrosoft Azure	1,128	+/-6	20,118	Microsoft Azure	MIT
360	guanaco-33b Non-commercial	1,127	+/-12	2,921	—	—
361	zephyr-7b-alpha MIT	1,126	+/-16	1,785	—	—
362	stripedhyena-nous-7b Apache 2.0	1,121	+/-11	5,182	—	—
363	CodeLlama-70B-InstructFacebook AI研究实验室	1,119	+/-18	1,143	Facebook AI研究实验室	Llama 2 Community
364	Gemma 1.1-2B-ITGoogle Research	1,116	+/-8	10,854	Google Research	Gemma license
365	vicuna-7b Llama 2 Community	1,115	+/-9	6,923	—	—
366	smollm2-1.7b-instruct Apache 2.0	1,114	+/-14	2,199	—	—
367	llama-3.2-1b-instructMeta	1,111	+/-8	8,045	Meta	Llama 3.2
368	Mistral 7B InstructMistralAI	1,110	+/-9	8,977	MistralAI	Apache 2.0
369	Baichuan2-7B-Chat百川智能	1,107	+/-7	14,148	百川智能	Llama 2 Community
370	Gemma 2B - ItGoogle Research	1,093	+/-11	4,780	Google Research	Gemma license
371	Qwen1.5-4B-Chat阿里巴巴	1,090	+/-9	7,597	阿里巴巴	Qianwen LICENSE
372	olmo-7b-instructAi2	1,073	+/-11	6,328	Ai2	Apache-2.0
373	Koala达摩院	1,070	+/-10	6,965	达摩院	—
374	alpaca-13b Non-commercial	1,069	+/-11	5,745	—	—
375	GPT4All 13BNomic AI	1,067	+/-15	1,743	Nomic AI	—
376	mpt-7b-chat CC-BY-NC-SA-4.0	1,062	+/-12	3,924	—	—
377	ChatGLM3-6B智谱AI	1,056	+/-12	4,658	智谱AI	—
378	RWKV-4-Raven-14B Apache 2.0	1,041	+/-11	4,845	—	—
379	ChatGLM2-6B智谱AI	1,024	+/-14	2,658	智谱AI	—
380	oasst-pythia-12b Apache 2.0	1,023	+/-11	6,310	—	—
381	ChatGLM-6B智谱AI	995	+/-13	4,914	智谱AI	—
382	fastchat-t5-3b Apache 2.0	992	+/-12	4,203	—	—
383	dolly-v2-12b MIT	981	+/-13	3,412	—	—
384	LLaMA 13BFacebook AI研究实验室	974	+/-16	2,391	Facebook AI研究实验室	Non-commercial
385	stablelm-tuned-alpha-7b CC-BY-NC-SA-4.0	952	+/-13	3,287	—	—

Data is for reference only. Official sources are authoritative. Click model names to view DataLearner model profiles.

FAQ

What is Text Generation Arena (LMArena)?

Text Generation Arena, formerly LMSYS Chatbot Arena, is one of the most widely followed anonymous LLM evaluation platforms. Users compare answers from two hidden models and vote for the better response; Elo-style scoring aggregates those votes into a dynamic leaderboard.

How is the Arena Elo score calculated?

Arena Elo is adapted from chess rating systems. After each head-to-head comparison, the preferred model gains rating points and the other model loses points, with the size of the change depending on the rating gap. The 95% confidence interval reflects how much comparison data supports the estimate.

Why do some models have both Thinking and regular versions?

Some models offer an extended-thinking mode that spends more inference time reasoning before producing the final answer. This can improve scores on reasoning, math, and coding tasks, but usually increases latency and cost, so Arena tracks these variants separately.

How should I choose an LLM from this leaderboard?

Consider overall Elo, cost, language coverage, open-source availability, and latency. The top-ranked model is not always the best fit for every workflow.