Text Arena🔬Life, Physical, & Social Science

View overall rankings across various AI models in text-to-text tasks across math, coding, creative writing, and other open-ended domains.

Apr 10, 2026

961,552 votes

337 models

	Rank Spread
1	17	claude-opus-4-6-thinking Anthropic · Proprietary	1519±12	2,516	$5 / $25	1M
2	17	gemini-3.1-pro-preview Google · Proprietary	1512±11	3,142	$2 / $12	1M
3	112	claude-opus-4-6 Anthropic · Proprietary	1511±12	2,659	$5 / $25	1M
4	122	gemini-3-pro Google · Proprietary	1500±8	6,742	$2 / $12	1M
5	130	glm-5.1 Z.ai · MIT	1499±20	836	$0.95 / $3.15	202.8K
6	144	muse-spark Meta · Proprietary	1494±27	462	N/A	N/A
7	130	claude-sonnet-4-6 Anthropic · Proprietary	1493±14	1,685	$3 / $15	1M
8	429	claude-opus-4-5-20251101-thinking-32k Anthropic · Proprietary	1490±8	5,826	$5 / $25	200K
9	429	grok-4.1-thinking xAI · Proprietary	1488±8	7,738	N/A	N/A
10	336	grok-4.20-multi-agent-beta-0309 xAI · Proprietary	1487±14	1,602	$2 / $6	2M
11	432	gemini-3-flash Google · Proprietary	1487±9	4,904	$0.50 / $3	1M
12	430	claude-opus-4-5-20251101 Anthropic · Proprietary	1487±8	7,286	$5 / $25	200K
13	433	gemini-3-flash (thinking-minimal) Google · Proprietary	1486±8	5,234	$0.50 / $3	1M
14	340	grok-4.20-beta-0309-reasoning xAI · Proprietary	1485±15	1,467	$2 / $6	2M
15	432	grok-4.1 xAI · Proprietary	1485±8	7,922	N/A	N/A
16	436	glm-5 Z.ai · MIT	1485±13	2,133	$1 / $3.20	202.8K
17	436	gpt-5.2-chat-latest-20260210 OpenAI · Proprietary	1485±12	2,422	$1.75 / $14	128K
18	342	grok-4.20-beta1 xAI · Proprietary	1484±16	1,445	N/A	N/A
19	342	mimo-v2-pro Xiaomi · Proprietary	1484±16	1,251	$1 / $3	1M
20	346	qwen3.5-max-preview Alibaba · Proprietary	1483±17	1,228	N/A	N/A
21	444	ernie-5.0-preview-1203 Baidu · Proprietary	1482±15	1,620	N/A	N/A
22	446	gpt-5.4-high OpenAI · Proprietary	1481±16	1,464	$2.50 / $15	1.1M
23	555	gpt-5.4-mini-high OpenAI · Proprietary	1474±17	1,142	$2.50 / $15	1.1M
24	1042	gemini-2.5-pro Google · Proprietary	1474±5	17,559	$1.25 / $10	1M
25	551	gpt-5.3-chat-latest OpenAI · Proprietary	1472±13	2,213	$1.75 / $14	128K
26	552	glm-4.7 Z.ai · MIT	1471±13	2,089	$0.39 / $1.75	202.8K
27	551	kimi-k2.5-thinking Moonshot · Modified MIT	1471±12	2,649	$0.60 / $3	N/A
28	1046	claude-opus-4-1-20250805-thinking-16k Anthropic · Proprietary	1471±7	7,933	$15 / $75	200K
29	1246	claude-sonnet-4-5-20250929 Anthropic · Proprietary	1471±7	9,402	$3 / $15	200K
30	754	dola-seed-2.0-pro Bytedance · Proprietary	1469±11	2,782	N/A	N/A
31	566	longcat-flash-chat-2602-exp Meituan · Proprietary	1468±20	867	N/A	N/A
32	562	gpt-5.4 OpenAI · Proprietary	1468±15	1,550	$2.50 / $15	1.1M
33	1354	gpt-5.1-high OpenAI · Proprietary	1466±8	6,636	$1.25 / $10	400K
34	1651	claude-sonnet-4-5-20250929-thinking-32k Anthropic · Proprietary	1466±7	9,458	$3 / $15	200K
35	572	gemma-4-31b Google · Apache 2.0	1464±20	869	$0.14 / $0.40	262.1K
36	1754	claude-opus-4-1-20250805 Anthropic · Proprietary	1463±6	12,119	$15 / $75	200K
37	1363	gemini-3.1-flash-lite-preview Google · Proprietary	1462±12	2,522	$0.25 / $1.50	1M
38	2258	chatgpt-4o-latest-20250326 OpenAI · Proprietary	1461±6	13,721	$5 / $15	128K
39	1666	qwen3.5-397b-a17b Alibaba · Apache 2.0	1460±12	2,435	$0.39 / $2.34	262.1K
40	2066	ernie-5.0-0110 Baidu · Proprietary	1458±10	3,592	N/A	N/A
41	2266	qwen3-max-preview Alibaba · Proprietary	1457±9	4,238	$0.78 / $3.90	262.1K
42	2665	o3-2025-04-16 OpenAI · Proprietary	1456±7	10,056	$2 / $8	200K
43	2671	gpt-5.1 OpenAI · Proprietary	1454±8	6,933	$1.25 / $10	400K
44	1680	kimi-k2.5-instant Moonshot · Modified MIT	1454±17	1,200	$0.38 / $1.72	262.1K
45	1390	deepseek-v3.1-terminus DeepSeek · MIT	1452±24	580	$0.21 / $0.79	163.8K
46	2673	gpt-5.2-high OpenAI · Proprietary	1452±9	4,805	$1.75 / $14	400K
47	2080	deepseek-v3.2-exp-thinking DeepSeek · MIT	1452±15	1,441	$0.27 / $0.41	163.8K
48	1685	gemma-4-26b-a4b Google · Apache 2.0	1452±19	889	N/A	N/A
49	2677	gpt-5.2 OpenAI · Proprietary	1451±9	4,311	$1.75 / $14	400K
50	3075	grok-4-1-fast-reasoning xAI · Proprietary	1450±8	6,711	$0.20 / $0.50	2M
51	2680	gpt-4.5-preview-2025-02-27 OpenAI · Proprietary	1449±12	2,545	$75 / $150	128K
52	3479	deepseek-v3.2 DeepSeek · MIT	1449±8	6,330	$0.26 / $0.38	163.8K
53	3380	gpt-5-chat OpenAI · Proprietary	1449±9	5,067	$1.25 / $10	128K
54	3580	glm-4.6 Z.ai · MIT	1447±8	5,874	$0.39 / $1.90	204.8K
55	17103	deepseek-v3.1-terminus-thinking DeepSeek · MIT	1445±25	547	$0.21 / $0.79	163.8K
56	3780	qwen3-235b-a22b-instruct-2507 Alibaba · Apache 2.0	1445±6	12,794	$0.26 / $1.06	N/A
57	3680	kimi-k2-thinking-turbo Moonshot · Modified MIT	1444±7	7,234	$1.15 / $8	262.1K
58	3581	gpt-5-high OpenAI · Proprietary	1444±9	5,135	$1.25 / $10	400K
59	3489	qwen3.5-27b Alibaba · Apache 2.0	1443±13	1,834	$0.20 / $1.56	262.1K
60	3591	kimi-k2-0905-preview Moonshot · Modified MIT	1441±14	1,745	$0.60 / $2.50	262.1K
61	3496	qwen3-vl-235b-a22b-instruct Alibaba · Apache 2.0	1441±15	1,759	$0.20 / $0.88	262.1K
62	4287	claude-opus-4-20250514-thinking-16k Anthropic · Proprietary	1440±8	6,016	$15 / $75	200K
63	4288	deepseek-v3.2-thinking DeepSeek · MIT	1439±8	5,701	$0.26 / $0.38	163.8K
64	29106	ernie-5.0-preview-1022 Baidu · Proprietary	1438±20	782	N/A	N/A
65	4389	gemini-2.5-flash-preview-09-2025 Google · Proprietary	1437±9	5,167	$0.30 / $2.50	1M
66	35107	grok-4-fast-chat xAI · Proprietary	1436±19	1,013	$3 / $15	256K
67	4590	grok-4-0709 xAI · Proprietary	1436±8	6,923	$3 / $15	256K
68	4299	deepseek-v3.1 DeepSeek · MIT	1435±12	2,338	$1.23 / $4.94	N/A
69	3899	deepseek-v3.2-exp DeepSeek · MIT	1435±14	1,916	$0.27 / $0.41	163.8K
70	30115	amazon-nova-experimental-chat-26-01-10 Amazon · Proprietary	1434±24	556	N/A	N/A
71	4499	grok-4-fast-reasoning xAI · Proprietary	1434±11	3,015	$0.20 / $0.50	2M
72	42103	qwen3.5-122b-a10b Alibaba · Apache 2.0	1434±13	1,935	$0.26 / $2.08	262.1K
73	4898	claude-opus-4-20250514 Anthropic · Proprietary	1432±8	7,126	$15 / $75	200K
74	4799	kimi-k2-0711-preview Moonshot · Modified MIT	1432±9	4,425	$0.60 / $2.50	131.1K
75	42107	qwen3-max-2025-09-23 Alibaba · Proprietary	1432±15	1,445	$0.78 / $3.90	262.1K
76	45108	deepseek-v3.1-thinking DeepSeek · MIT	1429±14	1,879	$1.23 / $4.94	N/A
77	5698	gemini-2.5-flash Google · Proprietary	1429±5	17,241	$0.30 / $2.50	1M
78	56104	mistral-large-3 Mistral · Apache 2.0	1427±8	6,078	$0.50 / $1.50	N/A
79	56101	mistral-medium-2508 Mistral · Proprietary	1427±6	12,036	$2.70 / $8.10	32K
80	37120	amazon-nova-experimental-chat-26-02-10 Amazon · Proprietary	1425±24	513	N/A	N/A
81	57106	gpt-4.1-2025-04-14 OpenAI · Proprietary	1425±7	8,606	$2 / $8	1M
82	56109	deepseek-r1-0528 DeepSeek · MIT	1424±11	3,446	$0.45 / $2.15	163.8K
83	55115	qwen3.5-flash Alibaba · Proprietary	1423±13	1,947	N/A	N/A
84	47120	gpt-5.4-nano-high OpenAI · Proprietary	1422±19	985	$2.50 / $15	1.1M
85	58114	glm-4.5 Z.ai · MIT	1422±10	3,913	$0.60 / $2.20	131.1K
86	61109	claude-haiku-4-5-20251001 Anthropic · Proprietary	1421±7	9,326	$1 / $5	200K
87	46123	hunyuan-t1-20250711 Tencent · Proprietary	1420±22	727	N/A	N/A
88	46128	amazon-nova-experimental-chat-12-10 Amazon · Proprietary	1419±23	601	N/A	N/A
89	64115	claude-sonnet-4-20250514-thinking-32k Anthropic · Proprietary	1418±8	5,734	$3 / $15	1M
90	63117	qwen3-next-80b-a3b-instruct Alibaba · Apache 2.0	1418±10	3,524	$0.09 / $1.10	262.1K
91	64115	grok-3-preview-02-24 xAI · Proprietary	1417±8	5,807	$3 / $15	131.1K
92	64115	qwen3-235b-a22b-no-thinking Alibaba · Apache 2.0	1417±8	6,365	$0.46 / $1.82	131.1K
93	64120	minimax-m2.5 MiniMax · Modified MIT	1415±12	2,694	$0.12 / $0.99	196.6K
94	71117	deepseek-v3-0324 DeepSeek · MIT	1414±7	7,710	$3 / $4.50	32.8K
95	72118	claude-sonnet-4-20250514 Anthropic · Proprietary	1413±8	6,506	$3 / $15	1M
96	64121	hunyuan-turbos-20250416 Tencent · Proprietary	1413±13	1,960	N/A	N/A
97	72120	o1-2024-12-17 OpenAI · Proprietary	1412±9	4,820	$15 / $60	200K
98	71120	deepseek-r1 DeepSeek · MIT	1411±10	3,309	$0.70 / $2.50	64K
99	65128	qwen3-235b-a22b-thinking-2507 Alibaba · Apache 2.0	1410±15	1,523	$0.15 / $1.50	131.1K
100	74127	minimax-m2.1-preview MiniMax · MIT	1408±12	2,659	$0.29 / $0.95	196.6K
101	79122	mistral-medium-2505 Mistral · Proprietary	1408±8	5,722	$0.40 / $2	131.1K
102	65136	minimax-m2.7 MiniMax · Proprietary	1407±18	1,107	$0.30 / $1.20	204.8K
103	67135	qwen3-vl-235b-a22b-thinking Alibaba · Apache 2.0	1407±17	1,261	$0.26 / $2.60	131.1K
104	77128	mai-1-preview Microsoft AI · Proprietary	1407±11	2,919	N/A	N/A
105	75132	qwen3.5-35b-a3b Alibaba · Apache 2.0	1406±13	1,982	$0.16 / $1.30	262.1K
106	82125	claude-3-7-sonnet-20250219-thinking-32k Anthropic · Proprietary	1405±8	6,804	$3 / $15	200K
107	82127	o4-mini-2025-04-16 OpenAI · Proprietary	1404±7	7,619	$1.10 / $4.40	200K
108	75135	longcat-flash-chat Meituan · MIT	1404±14	1,731	$0.20 / $0.80	131.1K
109	83127	gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary	1403±7	7,474	$0.10 / $0.40	1M
110	59153	glm-4.6v Z.ai · MIT	1403±27	467	$0.30 / $0.90	131.1K
111	57157	hunyuan-vision-1.5-thinking Tencent · Proprietary	1401±31	339	N/A	N/A
112	80139	trinity-large-preview Arcee AI · Apache 2.0	1401±13	2,088	N/A	N/A
113	82136	step-3.5-flash StepFun · Apache 2.0	1401±11	2,822	$0.10 / $0.30	262.1K
114	82142	mimo-v2-flash (thinking) Xiaomi · MIT	1399±14	1,699	$0.09 / $0.29	262.1K
115	88135	mimo-v2-flash (non-thinking) Xiaomi · MIT	1399±9	4,729	$0.09 / $0.29	262.1K
116	88137	qwen3-coder-480b-a35b-instruct Alibaba · Apache 2.0	1398±10	4,106	$0.40 / $1.60	262.1K
117	91140	glm-4.5-air Z.ai · MIT	1396±9	4,976	$0.13 / $0.85	131.1K
118	90142	gpt-5-mini-high OpenAI · Proprietary	1396±10	4,238	$0.25 / $2	400K
119	91142	qwen3-30b-a3b-instruct-2507 Alibaba · Apache 2.0	1394±10	3,704	$0.09 / $0.30	262.1K
120	97149	o1-preview OpenAI · Proprietary	1390±9	5,419	$15 / $60	N/A
121	100147	gemma-3-27b-it Google · Gemma	1390±7	7,973	$0.08 / $0.16	131.1K
122	99148	qwen2.5-max Alibaba · Proprietary	1390±8	5,716	N/A	N/A
123	106150	claude-3-7-sonnet-20250219 Anthropic · Proprietary	1387±8	7,517	$3 / $15	200K
124	103152	amazon-nova-experimental-chat-11-10 Amazon · Proprietary	1386±10	3,912	N/A	N/A
125	106151	gpt-4.1-mini-2025-04-14 OpenAI · Proprietary	1386±8	6,568	$0.40 / $1.60	1M
126	82173	amazon-nova-experimental-chat-10-09 Amazon · Proprietary	1385±28	435	N/A	N/A
127	107152	minimax-m1 MiniMax · Apache 2.0	1384±8	5,925	$0.40 / $2.20	1M
128	107153	gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary	1384±9	5,288	$0.10 / $0.40	1M
129	100157	glm-4.7-flash Z.ai · MIT	1383±14	1,806	$0.06 / $0.40	202.8K
130	107154	qwen3-235b-a22b Alibaba · Apache 2.0	1383±9	4,615	$0.46 / $1.82	131.1K
131	96166	qwen-plus-0125 Alibaba · Proprietary	1382±18	968	$0.40 / $1.20	131.1K
132	106160	qwen3-next-80b-a3b-thinking Alibaba · Apache 2.0	1380±13	2,145	$0.10 / $0.78	131.1K
133	110160	grok-3-mini-high xAI · Proprietary	1379±11	2,771	$0.30 / $0.50	131.1K
134	98173	qwen3-32b Alibaba · Apache 2.0	1378±20	798	$0.08 / $0.24	41K
135	118155	claude-3-5-sonnet-20241022 Anthropic · Proprietary	1377±6	15,667	$3 / $15	200K
136	99176	nvidia-llama-3.3-nemotron-super-49b-v1.5 Nvidia · Nvidia Open	1375±23	599	$0.10 / $0.40	131.1K
137	118166	deepseek-v3 DeepSeek · DeepSeek	1374±10	3,766	$1.14 / $4.56	N/A
138	118166	o3-mini-high OpenAI · Proprietary	1374±10	3,382	$1.10 / $4.40	200K
139	115169	amazon-nova-experimental-chat-10-20 Amazon · Proprietary	1373±14	1,855	N/A	N/A
140	121167	grok-3-mini-beta xAI · Proprietary	1371±10	3,923	$0.30 / $0.50	131.1K
141	124166	command-a-03-2025 Cohere · CC-BY-NC-4.0	1370±7	9,462	$2.50 / $10	256K
142	122173	mistral-small-2506 Mistral · Apache 2.0	1368±11	2,934	$0.10 / $0.30	32K
143	113185	intellect-3 Prime Intellect · MIT	1368±20	895	$0.20 / $1.10	131.1K
144	127169	gemini-2.0-flash-001 Google · Proprietary	1368±7	7,829	$0.10 / $0.40	1M
145	114187	gemma-3-12b-it Google · Gemma	1367±21	760	$0.04 / $0.13	131.1K
146	118186	ling-flash-2.0 Ant Group · MIT	1366±18	1,026	N/A	N/A
147	106199	hunyuan-turbo-0110 Tencent · Proprietary	1366±27	414	N/A	N/A
148	118187	glm-4-plus-0111 Zhipu · Proprietary	1366±19	986	N/A	N/A
149	119186	nvidia-nemotron-3-super-120b-a12b Nvidia · NVIDIA Open Model	1365±17	1,130	N/A	N/A
150	129174	llama-3.1-405b-instruct-bf16 Meta · Llama 3.1 Community	1364±7	7,177	$4 / $4	32.8K
151	128175	gemini-2.0-flash-lite-preview-02-05 Google · Proprietary	1363±9	4,444	$0.07 / $0.30	1M
152	129176	gpt-oss-120b OpenAI · Apache 2.0	1362±9	4,870	$0.04 / $0.19	131.1K
153	112206	llama-3.3-nemotron-49b-super-v1 Nvidia · Nvidia	1361±28	395	N/A	N/A
154	131175	gemini-1.5-pro-002 Google · Proprietary	1361±7	9,790	$3.50 / $10.50	2.1M
155	113205	hunyuan-turbos-20250226 Tencent · Proprietary	1361±28	384	N/A	N/A
156	115203	llama-3.1-nemotron-ultra-253b-v1 Nvidia · Nvidia Open Model	1361±26	498	$0.60 / $1.80	131.1K
157	120199	glm-4.5v Z.ai · MIT	1360±22	755	$0.60 / $1.80	65.5K
158	123197	minimax-m2 MiniMax · Apache 2.0	1358±18	1,119	$0.26 / $1	196.6K
159	133180	claude-3-5-sonnet-20240620 Anthropic · Proprietary	1357±7	13,749	$3 / $15	200K
160	131194	nova-2-lite Amazon · Proprietary	1356±13	2,064	$0.30 / $2.50	1M
161	137181	gpt-4o-2024-05-13 OpenAI · Proprietary	1356±7	19,017	$5 / $15	128K
162	133188	yi-lightning 01 AI · Proprietary	1355±10	4,822	N/A	N/A
163	138192	qwq-32b Alibaba · Apache 2.0	1352±9	4,559	$0.15 / $0.58	131.1K
164	140191	grok-2-2024-08-13 xAI · Proprietary	1352±7	10,796	$2 / $10	131.1K
165	140192	llama-3.1-405b-instruct-fp8 Meta · Llama 3.1 Community	1351±7	10,001	$4 / $4	32.8K
166	131206	step-3 StepFun · Apache 2.0	1351±18	1,082	$0.57 / $1.42	65.5K
167	143191	o3-mini OpenAI · Proprietary	1351±6	9,689	$1.10 / $4.40	200K
168	133204	gpt-4.1-nano-2025-04-14 OpenAI · Proprietary	1350±17	1,162	$0.10 / $0.40	1M
169	140194	gpt-4o-2024-08-06 OpenAI · Proprietary	1350±8	7,560	$2.50 / $10	128K
170	133215	step-2-16k-exp-202412 StepFun · Proprietary	1346±19	863	N/A	N/A
171	138210	gpt-5-nano-high OpenAI · Proprietary	1345±17	1,328	$0.05 / $0.40	400K
172	146202	gemini-advanced-0514 Google · Proprietary	1345±9	8,815	N/A	N/A
173	133217	hunyuan-large-2025-02-10 Tencent · Proprietary	1344±21	707	N/A	N/A
174	148202	llama-4-maverick-17b-128e-instruct Meta · Llama 4	1344±8	6,794	$0.63 / $1.80	131.1K
175	140210	olmo-3.1-32b-instruct Ai2 · Apache 2.0	1344±14	1,882	$0.20 / $0.60	65.5K
176	149201	claude-3-5-haiku-20241022 Anthropic · Proprietary	1343±6	11,978	$0.80 / $4	200K
177	150202	llama-3.3-70b-instruct Meta · Llama-3.3	1342±6	9,408	$0.10 / $0.32	131.1K
178	153202	claude-3-opus-20240229 Anthropic · Proprietary	1341±6	33,790	$15 / $75	200K
179	151204	o1-mini OpenAI · Proprietary	1341±7	8,979	$1.10 / $4.40	N/A
180	148212	athene-70b-0725 NexusFlow · CC-BY-NC-4.0	1339±12	3,029	N/A	N/A
181	150210	gemma-3n-e4b-it Google · Gemma	1338±10	3,717	$0.02 / $0.04	32.8K
182	148217	qwen2.5-plus-1127 Alibaba · Proprietary	1338±14	1,771	N/A	N/A
183	155210	athene-v2-chat NexusFlow · NexusFlow	1337±9	4,368	N/A	N/A
184	156212	llama-4-scout-17b-16e-instruct Meta · Llama	1336±9	5,047	$0.40 / $0.70	8.2K
185	148218	step-1o-turbo-202506 StepFun · Proprietary	1336±15	1,531	N/A	N/A
186	156216	glm-4-plus Zhipu AI · Proprietary	1335±10	4,702	$0.44 / $1.76	204.8K
187	162215	gemini-1.5-pro-001 Google · Proprietary	1334±8	13,570	$3.50 / $10.50	2.1M
188	144223	hunyuan-standard-2025-02-10 Tencent · Proprietary	1334±21	696	N/A	N/A
189	160216	qwen3-30b-a3b Alibaba · Apache 2.0	1334±9	4,633	$0.08 / $0.28	41K
190	162216	grok-2-mini-2024-08-13 xAI · Proprietary	1333±7	8,788	$2 / $10	131.1K
191	162217	mistral-large-2407 Mistral · Mistral Research	1332±8	7,485	$2 / $6	131.1K
192	150221	deepseek-v2.5-1210 DeepSeek · DeepSeek	1332±17	1,137	N/A	N/A
193	133236	mercury Inception AI · Proprietary	1331±36	289	$0.25 / $0.75	128K
194	156221	gpt-oss-20b OpenAI · Apache 2.0	1330±15	1,697	$0.03 / $0.14	131.1K
195	166218	gpt-4-turbo-2024-04-09 OpenAI · Proprietary	1329±7	16,354	$10 / $30	128K
196	165218	gemini-1.5-flash-002 Google · Proprietary	1329±8	6,083	$0.07 / $0.30	1M
197	171218	gpt-4o-mini-2024-07-18 OpenAI · Proprietary	1328±7	11,642	$0.15 / $0.60	128K
198	157227	ring-flash-2.0 Ant Group · MIT	1326±18	1,100	N/A	N/A
199	165221	qwen-max-0919 Alibaba · Qwen	1326±11	2,975	$1.60 / $6.40	32.8K
200	160232	olmo-3-32b-think Ai2 · Apache 2.0	1323±20	1,012	$0.15 / $0.50	65.5K
201	163230	reka-core-20240904 Reka AI · Proprietary	1322±16	1,183	N/A	N/A
202	176223	deepseek-v2.5 DeepSeek · DeepSeek	1322±10	4,318	N/A	N/A
203	176221	gpt-4-1106-preview OpenAI · Proprietary	1322±8	17,680	$10 / $30	128K
204	150236	mercury-2 Inception AI · Proprietary	1321±27	472	$0.25 / $0.75	128K
205	182223	llama-3.1-70b-instruct Meta · Llama 3.1 Community	1320±7	9,381	$0.40 / $0.40	131.1K
206	176228	nvidia-nemotron-3-nano-30b-a3b-bf16 Nvidia · NVIDIA Open Model	1320±12	2,489	$0.06 / $0.24	262.1K
207	182226	qwen2.5-72b-instruct Alibaba · Qwen	1319±8	6,932	$1.20 / $1.20	N/A
208	182226	gpt-4-0125-preview OpenAI · Proprietary	1319±8	16,044	$10 / $30	128K
209	163236	ibm-granite-h-small IBM · Apache 2.0	1318±21	907	N/A	N/A
210	173232	llama-3.1-nemotron-70b-instruct Nvidia · Llama 3.1	1317±16	1,299	$1.20 / $1.20	131.1K
211	187228	mistral-large-2411 Mistral · MRL	1316±9	4,869	$2 / $6	131.1K
212	176232	jamba-1.5-large AI21 Labs · Jamba Open	1315±16	1,358	$2 / $8	256K
213	170236	gemma-3-4b-it Google · Gemma	1314±21	780	$0.04 / $0.08	131.1K
214	180234	magistral-medium-2506 Mistral · Proprietary	1313±15	1,960	$2 / $5	40K
215	174242	llama-3.1-tulu-3-70b Ai2 · Llama 3.1	1308±25	520	N/A	N/A
216	179240	hunyuan-large-vision Tencent · Proprietary	1307±20	933	N/A	N/A
217	194234	mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0	1307±9	5,308	$0.10 / $0.30	32K
218	190238	olmo-3.1-32b-think Ai2 · Apache 2.0	1306±17	1,409	$0.15 / $0.50	65.5K
219	201234	gemma-2-27b-it Google · Gemma license	1305±7	12,863	$0.65 / $0.65	8.2K
220	198236	amazon-nova-pro-v1.0 Amazon · Proprietary	1305±9	4,281	$0.80 / $3.20	300K
221	184242	llama-3.1-nemotron-51b-instruct Nvidia · Llama 3.1	1304±22	682	N/A	N/A
222	194238	command-r-plus-08-2024 Cohere · CC-BY-NC-4.0	1304±15	1,639	$2.50 / $10	128K
223	194236	nemotron-4-340b-instruct Nvidia · NVIDIA Open Model	1304±12	3,316	N/A	N/A
224	203236	claude-3-sonnet-20240229 Anthropic · Proprietary	1301±8	19,089	$3 / $15	200K
225	198243	reka-flash-20240904 Reka AI · Proprietary	1297±16	1,277	N/A	N/A
226	207238	llama-3-70b-instruct Meta · Llama 3 Community	1297±7	25,903	$0.51 / $0.74	8.2K
227	201243	gemma-2-9b-it-simpo Princeton · MIT	1297±15	1,596	$0.03 / $0.09	8.2K
228	207240	gemini-1.5-flash-001 Google · Proprietary	1295±8	10,875	$0.07 / $0.30	1M
229	206242	mistral-small-24b-instruct-2501 Mistral · Apache 2.0	1295±12	2,579	$0.05 / $0.08	32.8K
230	204243	glm-4-0520 Zhipu AI · Proprietary	1292±15	1,590	N/A	N/A
231	206243	command-r-08-2024 Cohere · CC-BY-NC-4.0	1292±15	1,620	$0.15 / $0.60	128K
232	210243	command-r-plus Cohere · CC-BY-NC-4.0	1290±8	13,227	$2.50 / $10	128K
233	210243	gpt-4-0314 OpenAI · Proprietary	1289±9	9,610	$30 / $60	8.2K
234	201252	olmo-2-0325-32b-instruct Ai2 · Apache-2.0	1288±24	580	$0.05 / $0.20	128K
235	213243	c4ai-aya-expanse-32b Cohere · CC-BY-NC-4.0	1288±9	4,768	N/A	N/A
236	220245	qwen2-72b-instruct Alibaba · Qianwen LICENSE	1282±9	6,456	$0.90 / $0.90	32.8K
237	220246	amazon-nova-lite-v1.0 Amazon · Proprietary	1282±10	3,333	$0.06 / $0.24	300K
238	223245	gemma-2-9b-it Google · Gemma license	1281±7	9,169	$0.03 / $0.09	8.2K
239	223246	gpt-4-0613 OpenAI · Proprietary	1279±8	15,252	$30 / $60	8.2K
240	213257	qwen2.5-coder-32b-instruct Alibaba · Apache 2.0	1279±18	956	$0.87 / $0.87	32K
241	225249	gemini-1.5-flash-8b-001 Google · Proprietary	1278±8	6,236	$0.07 / $0.30	1M
242	228250	claude-3-haiku-20240307 Anthropic · Proprietary	1275±7	20,565	$0.25 / $1.25	200K
243	225260	deepseek-coder-v2 DeepSeek · DeepSeek License	1272±13	2,552	$0.14 / $0.28	128K
244	235261	phi-4 Microsoft · MIT	1266±10	4,245	$0.07 / $0.14	16.4K
245	235262	reka-flash-21b-20240226-online Reka AI · Proprietary	1262±14	2,572	N/A	N/A
246	240262	amazon-nova-micro-v1.0 Amazon · Proprietary	1258±11	3,314	$0.04 / $0.14	128K
247	239264	gemini-pro-dev-api Google · Proprietary	1257±14	3,251	$0.35 / $1.05	32.8K
248	237265	jamba-1.5-mini AI21 Labs · Jamba Open	1256±16	1,490	$0.20 / $0.40	256K
249	242262	mistral-large-2402 Mistral · Proprietary	1254±9	10,875	$4 / $12	32K
250	241263	mistral-medium Mistral · Proprietary	1254±11	6,062	$2.70 / $8.10	32K
251	242262	mixtral-8x22b-instruct-v0.1 Mistral · Apache 2.0	1253±9	8,677	$0.90 / $0.90	65.5K
252	243264	command-r Cohere · CC-BY-NC-4.0	1251±9	9,216	$0.15 / $0.60	128K
253	241267	c4ai-aya-expanse-8b Cohere · CC-BY-NC-4.0	1251±14	1,689	N/A	N/A
254	239269	ministral-8b-2410 Mistral · MRL	1250±20	827	$0.10 / $0.10	131.1K
255	243265	qwen1.5-110b-chat Alibaba · Qianwen LICENSE	1250±11	4,398	N/A	N/A
256	244265	qwen1.5-72b-chat Alibaba · Qianwen LICENSE	1249±10	6,892	N/A	N/A
257	243265	reka-flash-21b-20240226 Reka AI · Proprietary	1249±12	4,108	N/A	N/A
258	245265	llama-3-8b-instruct Meta · Llama 3 Community	1246±8	17,322	$0.03 / $0.04	8.2K
259	239276	hunyuan-standard-256k Tencent · Proprietary	1244±25	538	N/A	N/A
260	242275	zephyr-orpo-141b-A35b-v0.1 HuggingFace · Apache 2.0	1242±21	827	N/A	N/A
261	242274	gemini-pro Google · Proprietary	1242±21	1,125	$0.35 / $1.05	32.8K
262	242279	llama-3.1-tulu-3-8b Ai2 · Llama 3.1	1236±25	516	N/A	N/A
263	250274	yi-1.5-34b-chat 01 AI · Apache-2.0	1232±11	4,292	N/A	N/A
264	257274	llama-3.1-8b-instruct Meta · Llama 3.1 Community	1229±8	8,403	$0.02 / $0.05	16.4K
265	258277	gpt-3.5-turbo-0125 OpenAI · Proprietary	1227±8	11,407	$0.50 / $1.50	16.4K
266	257277	phi-3-medium-4k-instruct Microsoft · MIT	1226±11	4,186	$0.17 / $0.68	N/A
267	258279	qwen1.5-32b-chat Alibaba · Qianwen LICENSE	1223±12	3,861	N/A	N/A
268	252296	granite-3.0-8b-instruct IBM · Apache 2.0	1220±20	1,128	N/A	N/A
269	249297	granite-3.1-8b-instruct IBM · Apache 2.0	1218±25	560	N/A	N/A
270	259280	mixtral-8x7b-instruct-v0.1 Mistral · Apache 2.0	1217±8	12,824	$0.63 / $0.63	32K
271	259296	yi-34b-chat 01 AI · Yi License	1215±13	2,658	$0.90 / $0.90	4.1K
272	259295	dbrx-instruct-preview Databricks · DBRX LICENSE	1215±12	5,642	$0.60 / $0.60	32.8K
273	259287	gemma-2-2b-it Google · Gemma license	1215±8	7,909	N/A	N/A
274	259297	internlm2_5-20b-chat InternLM · Other	1211±15	1,700	$0 / $0	32.8K
275	263297	starling-lm-7b-beta Nexusflow · Apache-2.0	1206±14	2,912	N/A	N/A
276	264300	gpt-3.5-turbo-1106 OpenAI · Proprietary	1204±15	3,046	$1 / $2	16.4K
277	262302	wizardlm-70b Microsoft · Llama 2 Community	1203±18	1,334	N/A	N/A
278	266305	starling-lm-7b-alpha UC Berkeley · CC-BY-NC-4.0	1197±15	1,854	N/A	N/A
279	269300	llama-2-70b-chat Meta · Llama 2 Community	1197±10	6,638	$0.70 / $2.80	4.1K
280	269302	gemma-1.1-7b-it Google · Gemma license	1197±11	4,147	$0.03 / $0.09	8.2K
281	269302	snowflake-arctic-instruct Snowflake · Apache 2.0	1197±12	5,411	N/A	N/A
282	269304	phi-3-small-8k-instruct Microsoft · MIT	1195±12	3,117	$0.15 / $0.60	N/A
283	270304	vicuna-33b LMSYS · Non-commercial	1195±12	3,986	$0 / $0	2K
284	270306	qwen1.5-14b-chat Alibaba · Qianwen LICENSE	1193±13	3,116	$0.30 / $0.30	N/A
285	268310	tulu-2-dpo-70b AllenAI/UW · AI2 ImpACT Low-risk	1192±19	1,112	N/A	N/A
286	269310	openchat-3.5 OpenChat · Apache-2.0	1191±18	1,439	$0.20 / $0.20	N/A
287	266311	nous-hermes-2-mixtral-8x7b-dpo NousResearch · Apache-2.0	1190±23	651	$0.90 / $0.90	N/A
288	270310	llama-3.2-3b-instruct Meta · Llama 3.2	1187±18	1,355	$0.05 / $0.34	80K
289	270311	openhermes-2.5-mistral-7b NousResearch · Apache-2.0	1186±20	884	$0.17 / $0.17	N/A
290	273310	openchat-3.5-0106 OpenChat · Apache-2.0	1185±14	2,209	N/A	N/A
291	270311	deepseek-llm-67b-chat DeepSeek · DeepSeek License	1184±22	876	N/A	N/A
292	271311	granite-3.0-2b-instruct IBM · Apache 2.0	1184±19	1,206	N/A	N/A
293	269312	llama2-70b-steerlm-chat Nvidia · Llama 2 Community	1183±24	642	N/A	N/A
294	270313	solar-10.7b-instruct-v1.0 Upstage AI · CC-BY-NC-4.0	1181±23	721	$0.30 / $0.30	N/A
295	270316	granite-3.1-2b-instruct IBM · Apache 2.0	1179±27	549	N/A	N/A
296	278311	mistral-7b-instruct-v0.2 Mistral · Apache-2.0	1174±13	3,284	$0.20 / $0.20	32.8K
297	269319	dolphin-2.2.1-mistral-7b Cognitive Computations · Apache-2.0	1174±34	308	$0.50 / $0.50	16.4K
298	276315	wizardlm-13b Microsoft · Llama 2 Community	1173±18	1,246	$0.30 / $0.30	N/A
299	281318	codellama-34b-instruct Meta · Llama 2 Community	1166±18	1,225	$0.35 / $1.40	16.4K
300	270323	falcon-180b-chat TII · Falcon-180B TII License	1165±41	206	N/A	N/A
301	276320	guanaco-33b UW · Non-commercial	1164±26	526	N/A	N/A
302	283318	palm-2 Google · Proprietary	1164±18	1,368	$0.50 / $0.50	25.8K
303	281319	qwen1.5-7b-chat Alibaba · Qianwen LICENSE	1163±21	828	$0.20 / $0.20	N/A
304	285318	phi-3-mini-4k-instruct-june-2024 Microsoft · MIT	1162±15	1,956	$0.13 / $0.52	4.1K
305	278321	qwq-32b-preview Alibaba · Apache 2.0	1161±26	583	$0.15 / $0.58	131.1K
306	285318	llama-2-13b-chat Meta · Llama 2 Community	1161±13	3,270	$0.25 / $0.25	4.1K
307	285319	zephyr-7b-beta HuggingFace · MIT	1160±16	1,996	$0.15 / $0.15	16.4K
308	289319	vicuna-13b LMSYS · Llama 2 Community	1156±13	3,288	$0.30 / $0.30	N/A
309	284322	mpt-30b-chat MosaicML · CC-BY-NC-SA-4.0	1156±26	509	N/A	N/A
310	276323	smollm2-1.7b-instruct HuggingFace · Apache 2.0	1154±35	352	N/A	N/A
311	294321	phi-3-mini-4k-instruct Microsoft · MIT	1148±13	3,517	$0.13 / $0.52	N/A
312	285323	zephyr-7b-alpha HuggingFace · MIT	1144±34	294	N/A	N/A
313	297322	phi-3-mini-128k-instruct Microsoft · MIT	1141±14	3,426	$0.13 / $0.52	N/A
314	296323	gemma-7b-it Google · Gemma license	1140±17	1,588	$0.05 / $0.08	8.2K
315	295323	qwen-14b-chat Alibaba · Qianwen LICENSE	1137±21	894	N/A	N/A
316	296323	stripedhyena-nous-7b Together AI · Apache 2.0	1135±21	863	$0.20 / $0.20	N/A
317	298323	llama-3.2-1b-instruct Meta · Llama 3.2	1133±18	1,407	$0.03 / $0.20	60K
318	298323	mistral-7b-instruct Mistral · Apache 2.0	1131±18	1,577	$0.07 / $0.28	4.1K
319	302323	gemma-1.1-2b-it Google · Gemma license	1128±16	1,929	N/A	N/A
320	307323	llama-2-7b-chat Meta · Llama 2 Community	1124±13	2,474	$0.15 / $0.15	4.1K
321	306324	vicuna-7b LMSYS · Llama 2 Community	1120±19	1,171	$0.20 / $0.20	N/A
322	309328	qwen1.5-4b-chat Alibaba · Qianwen LICENSE	1111±19	1,277	$0.10 / $0.10	N/A
323	311329	koala-13b UC Berkeley · Non-commercial	1106±21	1,211	N/A	N/A
324	321332	alpaca-13b Stanford · Non-commercial	1081±22	986	N/A	N/A
325	322332	gemma-2b-it Google · Gemma license	1078±23	879	$0.10 / $0.10	N/A
326	322332	olmo-7b-instruct Ai2 · Apache-2.0	1077±20	1,169	$0.20 / $0.20	N/A
327	322332	mpt-7b-chat MosaicML · CC-BY-NC-SA-4.0	1069±25	677	N/A	N/A
328	323332	RWKV-4-Raven-14B RWKV · Apache 2.0	1066±24	844	N/A	N/A
329	322333	gpt4all-13b-snoozy Nomic AI · Non-commercial	1063±36	305	N/A	N/A
330	324333	chatglm3-6b Tsinghua · Apache-2.0	1052±23	888	N/A	N/A
331	324333	oasst-pythia-12b OpenAssistant · Apache 2.0	1049±21	1,134	N/A	N/A
332	324335	chatglm2-6b Tsinghua · Apache-2.0	1044±30	436	N/A	N/A
333	329337	llama-13b Meta · Non-commercial	997±33	414	$0.23 / $0.23	N/A
334	332336	fastchat-t5-3b LMSYS · Apache 2.0	997±25	685	N/A	N/A
335	332337	dolly-v2-12b Databricks · MIT	988±29	589	N/A	N/A
336	333337	chatglm-6b Tsinghua · Non-commercial	959±26	819	N/A	N/A
337	334337	stablelm-tuned-alpha-7b Stability AI · CC-BY-NC-SA-4.0	939±27	615	N/A	N/A

Text Arena🔬Life, Physical, & Social Science

Default Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

Fraction of Model A Wins for All Non-tied A vs. B Battles

Average Win Rate Against All Other Models (Uniform Sampling and No Ties)