Text Arena | Math

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

Feb 26, 2026

531,695 votes

306 models

	Rank Spread
1	110	gemini-3.1-pro-preview Google · Proprietary	1524±35	267
2	18	claude-opus-4-6-thinking Anthropic · Proprietary	1522±28	414
3	114	gpt-5.2-chat-latest-20260210 OpenAI · Proprietary	1520±38	237
4	116	claude-opus-4-6 Anthropic · Proprietary	1507±27	472
5	219	gemini-3-pro Google · Proprietary	1482±12	2,471
6	135	grok-4.20-beta1 xAI · Proprietary	1478±34	260
7	142	claude-sonnet-4-6 Anthropic · Proprietary	1477±35	246
8	221	gemini-3-flash Google · Proprietary	1477±14	1,896
9	138	dola-seed-2.0-preview Bytedance · Proprietary	1475±32	306
10	131	kimi-k2.5-thinking Moonshot · Modified MIT	1475±22	678
11	323	claude-opus-4-5-20251101 Anthropic · Proprietary	1472±13	2,189
12	331	gpt-5.2-high OpenAI · Proprietary	1471±17	1,230
13	328	claude-opus-4-5-20251101-thinking-32k Anthropic · Proprietary	1470±14	1,819
14	433	gemini-3-flash (thinking-minimal) Google · Proprietary	1466±16	1,309
15	339	ernie-5.0-0110 Baidu · Proprietary	1463±20	825
16	534	gpt-5.1-high OpenAI · Proprietary	1461±13	2,106
17	533	claude-sonnet-4-5-20250929-thinking-32k Anthropic · Proprietary	1460±11	2,896
18	470	glm-5 Z.ai · MIT	1453±27	421
19	738	o3-2025-04-16 OpenAI · Proprietary	1452±10	3,847
20	839	gemini-2.5-pro Google · Proprietary	1451±8	6,038
21	649	grok-4.1-thinking xAI · Proprietary	1450±13	2,204
22	852	claude-opus-4-1-20250805-thinking-16k Anthropic · Proprietary	1446±11	3,004
23	585	qwen3.5-397b-a17b Alibaba · Apache 2.0	1444±30	342
24	869	qwen3-max-preview Alibaba · Proprietary	1442±15	1,514
25	964	kimi-k2-thinking-turbo Moonshot · Modified MIT	1442±13	2,193
26	772	gpt-5.2 OpenAI · Proprietary	1441±19	971
27	686	kimi-k2.5-instant Moonshot · Modified MIT	1440±27	442
28	1170	gpt-5-high OpenAI · Proprietary	1439±14	1,912
29	1370	grok-4-0709 xAI · Proprietary	1436±12	2,276
30	1570	claude-opus-4-1-20250805 Anthropic · Proprietary	1435±9	4,732
31	892	qwen3-max-2025-09-23 Alibaba · Proprietary	1433±24	581
32	1189	glm-4.7 Z.ai · MIT	1432±21	711
33	899	grok-4-fast-chat xAI · Proprietary	1430±29	401
34	2078	grok-4.1 xAI · Proprietary	1429±12	2,705
35	995	deepseek-v3.2-exp-thinking DeepSeek · MIT	1429±27	473
36	1983	deepseek-v3.2 DeepSeek · MIT	1429±14	1,977
37	2280	qwen3-235b-a22b-instruct-2507 Alibaba · Apache 2.0	1426±9	4,364
38	2093	qwen3-next-80b-a3b-instruct Alibaba · Apache 2.0	1425±17	1,201
39	2187	claude-sonnet-4-5-20250929 Anthropic · Proprietary	1424±11	2,933
40	2189	glm-4.6 Z.ai · MIT	1424±13	2,090
41	1596	deepseek-v3.2-exp DeepSeek · MIT	1422±21	771
42	15100	longcat-flash-chat Meituan · MIT	1422±22	684
43	2292	gpt-5.1 OpenAI · Proprietary	1421±12	2,440
44	19102	deepseek-v3.1-thinking DeepSeek · MIT	1420±22	669
45	2292	claude-opus-4-20250514-thinking-16k Anthropic · Proprietary	1420±12	2,332
46	2393	o4-mini-2025-04-16 OpenAI · Proprietary	1418±11	3,016
47	21100	deepseek-v3.1 DeepSeek · MIT	1418±18	1,007
48	2295	glm-4.5 Z.ai · MIT	1418±15	1,446
49	2295	gpt-5-chat OpenAI · Proprietary	1417±14	1,793
50	20105	kimi-k2-0905-preview Moonshot · Modified MIT	1416±21	762
51	2295	grok-4-1-fast-reasoning xAI · Proprietary	1416±14	1,939
52	20106	qwen3-vl-235b-a22b-instruct Alibaba · Apache 2.0	1416±23	708
53	9119	deepseek-v3.1-terminus-thinking DeepSeek · MIT	1416±40	203
54	20109	minimax-m2.5 MiniMax · Modified MIT	1415±27	414
55	2397	gemini-2.5-flash-preview-09-2025 Google · Proprietary	1415±13	1,907
56	22104	grok-4-fast-reasoning xAI · Proprietary	1414±18	1,066
57	2994	gemini-2.5-flash Google · Proprietary	1414±8	6,239
58	21107	ernie-5.0-preview-1203 Baidu · Proprietary	1414±23	624
59	23103	gpt-4.5-preview-2025-02-27 OpenAI · Proprietary	1413±15	1,384
60	23103	deepseek-v3.2-thinking DeepSeek · MIT	1413±15	1,541
61	23104	gpt-5-mini-high OpenAI · Proprietary	1413±16	1,446
62	24101	deepseek-r1 DeepSeek · MIT	1413±14	1,609
63	20112	qwen3-vl-235b-a22b-thinking Alibaba · Apache 2.0	1412±29	414
64	2897	o1-2024-12-17 OpenAI · Proprietary	1412±11	2,980
65	14116	ernie-5.0-preview-1022 Baidu · Proprietary	1412±35	263
66	28104	o3-mini-high OpenAI · Proprietary	1409±13	1,906
67	19119	amazon-nova-experimental-chat-26-01-10 Amazon · Proprietary	1408±34	258
68	22112	qwen3-235b-a22b-thinking-2507 Alibaba · Apache 2.0	1407±24	505
69	29106	claude-sonnet-4-20250514-thinking-32k Anthropic · Proprietary	1406±13	2,102
70	33103	chatgpt-4o-latest-20250326 OpenAI · Proprietary	1406±8	5,814
71	17124	hunyuan-t1-20250711 Tencent · Proprietary	1405±38	242
72	31105	claude-opus-4-20250514 Anthropic · Proprietary	1405±11	2,879
73	29108	mistral-large-3 Mistral · Apache 2.0	1404±14	1,734
74	35106	mistral-medium-2508 Mistral · Proprietary	1403±9	4,167
75	22119	qwen3-32b Alibaba · Apache 2.0	1403±30	316
76	20125	amazon-nova-experimental-chat-12-10 Amazon · Proprietary	1402±36	239
77	32109	minimax-m1 MiniMax · Apache 2.0	1401±13	1,991
78	29115	deepseek-r1-0528 DeepSeek · MIT	1399±19	911
79	35112	qwen3-235b-a22b Alibaba · Apache 2.0	1398±14	1,640
80	31115	minimax-m2.1-preview MiniMax · MIT	1398±18	1,028
81	30116	qwen3-next-80b-a3b-thinking Alibaba · Apache 2.0	1398±20	824
82	32114	amazon-nova-experimental-chat-11-10 Amazon · Proprietary	1398±17	1,173
83	37110	qwen3-235b-a22b-no-thinking Alibaba · Apache 2.0	1398±12	2,507
84	30116	mai-1-preview Microsoft AI · Proprietary	1398±19	892
85	29119	step-3.5-flash StepFun · Apache 2.0	1397±24	548
86	40110	claude-haiku-4-5-20251001 Anthropic · Proprietary	1397±11	2,859
87	31119	amazon-nova-experimental-chat-10-20 Amazon · Proprietary	1396±20	796
88	22130	deepseek-v3.1-terminus DeepSeek · MIT	1395±39	216
89	37115	glm-4.5-air Z.ai · MIT	1395±15	1,552
90	22130	nvidia-llama-3.3-nemotron-super-49b-v1.5 Nvidia · Nvidia Open	1393±39	193
91	42115	kimi-k2-0711-preview Moonshot · Modified MIT	1393±14	1,772
92	37119	grok-3-mini-high xAI · Proprietary	1392±18	1,007
93	47115	claude-sonnet-4-20250514 Anthropic · Proprietary	1391±11	2,596
94	53116	claude-3-7-sonnet-20250219-thinking-32k Anthropic · Proprietary	1388±11	2,857
95	58116	o1-preview OpenAI · Proprietary	1388±9	4,570
96	51119	gpt-oss-120b OpenAI · Apache 2.0	1387±14	1,808
97	50122	qwen3-30b-a3b-instruct-2507 Alibaba · Apache 2.0	1386±15	1,433
98	63116	o3-mini OpenAI · Proprietary	1385±8	4,803
99	48124	mimo-v2-flash (non-thinking) Xiaomi · MIT	1385±17	1,200
100	34130	intellect-3 Prime Intellect · MIT	1383±31	335
101	29135	llama-3.1-nemotron-ultra-253b-v1 Nvidia · Nvidia Open Model	1382±37	209
102	61125	qwen3-coder-480b-a35b-instruct Alibaba · Apache 2.0	1381±14	1,687
103	43128	mimo-v2-flash (thinking) Xiaomi · MIT	1381±22	640
104	66124	grok-3-preview-02-24 xAI · Proprietary	1380±11	2,763
105	72126	gpt-4.1-2025-04-14 OpenAI · Proprietary	1375±10	3,327
106	72126	deepseek-v3-0324 DeepSeek · MIT	1375±10	3,270
107	70128	grok-3-mini-beta xAI · Proprietary	1373±14	1,610
108	75128	gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary	1370±11	2,870
109	75129	gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary	1369±12	2,167
110	81128	qwen2.5-max Alibaba · Proprietary	1369±10	3,357
111	50136	step-3 StepFun · Apache 2.0	1369±32	345
112	67135	glm-4.7-flash Z.ai · MIT	1367±23	644
113	76130	qwq-32b Alibaba · Apache 2.0	1367±13	1,759
114	94130	o1-mini OpenAI · Proprietary	1365±8	7,502
115	54141	glm-4.5v Z.ai · MIT	1364±34	272
116	54143	minimax-m2 MiniMax · Apache 2.0	1363±35	292
117	68138	ling-flash-2.0 Ant Group · MIT	1363±27	454
118	94130	claude-3-7-sonnet-20250219 Anthropic · Proprietary	1362±10	3,451
119	98131	gemini-2.0-flash-001 Google · Proprietary	1359±9	4,164
120	95132	gpt-4.1-mini-2025-04-14 OpenAI · Proprietary	1358±11	2,774
121	94135	qwen3-30b-a3b Alibaba · Apache 2.0	1357±13	1,773
122	87135	nvidia-nemotron-3-nano-30b-a3b-bf16 Nvidia · NVIDIA Open Model	1357±19	989
123	100135	mistral-medium-2505 Mistral · Proprietary	1354±12	2,343
124	107135	claude-3-5-sonnet-20241022 Anthropic · Proprietary	1351±6	10,151
125	95140	hunyuan-turbos-20250416 Tencent · Proprietary	1351±19	878
126	87147	gpt-5-nano-high OpenAI · Proprietary	1350±27	489
127	87147	ring-flash-2.0 Ant Group · MIT	1349±27	459
128	102144	mistral-small-2506 Mistral · Apache 2.0	1343±17	1,073
129	113136	claude-3-5-sonnet-20240620 Anthropic · Proprietary	1343±7	11,360
130	115140	gemini-1.5-pro-002 Google · Proprietary	1340±7	7,610
131	102156	gpt-oss-20b OpenAI · Apache 2.0	1339±22	689
132	106155	nova-2-lite Amazon · Proprietary	1338±20	833
133	121155	gemini-2.0-flash-lite-preview-02-05 Google · Proprietary	1328±10	2,804
134	115165	qwen-plus-0125 Alibaba · Proprietary	1328±19	733
135	124157	gemma-3-27b-it Google · Gemma	1326±9	3,683
136	124160	llama-4-maverick-17b-128e-instruct Meta · Llama 4	1324±11	2,941
137	128160	llama-3.1-405b-instruct-fp8 Meta · Llama 3.1 Community	1321±7	8,484
138	114180	gemma-3-12b-it Google · Gemma	1321±27	389
139	129164	llama-3.1-405b-instruct-bf16 Meta · Llama 3.1 Community	1318±8	5,207
140	123177	step-2-16k-exp-202412 StepFun · Proprietary	1316±20	640
141	127171	llama-4-scout-17b-16e-instruct Meta · Llama	1316±13	2,013
142	129167	athene-v2-chat NexusFlow · NexusFlow	1315±9	3,413
143	129170	deepseek-v3 DeepSeek · DeepSeek	1315±11	2,724
144	131165	claude-3-opus-20240229 Anthropic · Proprietary	1314±6	25,771
145	115193	olmo-3-32b-think Ai2 · Apache 2.0	1313±32	306
146	131170	command-a-03-2025 Cohere · CC-BY-NC-4.0	1312±9	4,087
147	131170	gpt-4o-2024-08-06 OpenAI · Proprietary	1311±8	6,827
148	131174	yi-lightning 01 AI · Proprietary	1309±10	3,922
149	131178	qwen2.5-plus-1127 Alibaba · Proprietary	1308±14	1,406
150	126186	step-1o-turbo-202506 StepFun · Proprietary	1308±23	636
151	135172	gpt-4o-2024-05-13 OpenAI · Proprietary	1307±6	15,102
152	127190	olmo-3.1-32b-instruct Ai2 · Apache 2.0	1306±23	691
153	137175	gpt-4-1106-preview OpenAI · Proprietary	1306±8	13,306
154	135177	gemini-advanced-0514 Google · Proprietary	1306±9	6,393
155	123196	hunyuan-turbos-20250226 Tencent · Proprietary	1305±31	238
156	138179	gpt-4-0125-preview OpenAI · Proprietary	1302±8	12,375
157	131193	glm-4-plus-0111 Zhipu · Proprietary	1300±19	720
158	140183	qwen2.5-72b-instruct Alibaba · Qwen	1299±8	5,419
159	140183	llama-3.3-70b-instruct Meta · Llama-3.3	1299±7	5,852
160	141183	gpt-4-turbo-2024-04-09 OpenAI · Proprietary	1299±7	13,219
161	141184	gemini-1.5-pro-001 Google · Proprietary	1298±8	10,486
162	131197	hunyuan-large-2025-02-10 Tencent · Proprietary	1296±24	497
163	144184	grok-2-2024-08-13 xAI · Proprietary	1296±7	8,953
164	137194	deepseek-v2.5-1210 DeepSeek · DeepSeek	1295±17	1,033
165	140190	qwen-max-0919 Alibaba · Qwen	1295±12	2,250
166	131197	olmo-3.1-32b-think Ai2 · Apache 2.0	1294±26	476
167	133197	hunyuan-standard-2025-02-10 Tencent · Proprietary	1293±24	499
168	134197	magistral-medium-2506 Mistral · Proprietary	1292±25	580
169	147190	gemini-1.5-flash-002 Google · Proprietary	1291±8	4,791
170	148190	mistral-large-2407 Mistral · Mistral Research	1290±8	6,662
171	146193	glm-4-plus Zhipu AI · Proprietary	1290±10	3,600
172	146193	deepseek-v2.5 DeepSeek · DeepSeek	1290±10	3,651
173	135206	hunyuan-large-vision Tencent · Proprietary	1287±29	371
174	151193	claude-3-5-haiku-20241022 Anthropic · Proprietary	1287±7	6,438
175	152196	mistral-large-2411 Mistral · MRL	1285±9	3,563
176	153196	gpt-4-0314 OpenAI · Proprietary	1284±9	7,050
177	137208	hunyuan-turbo-0110 Tencent · Proprietary	1282±31	243
178	148201	llama-3.1-nemotron-70b-instruct Nvidia · Llama 3.1	1281±17	1,041
179	153197	mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0	1280±13	2,226
180	137208	ibm-granite-h-small IBM · Apache 2.0	1280±31	360
181	158197	gpt-4o-mini-2024-07-18 OpenAI · Proprietary	1279±7	9,345
182	145206	gpt-4.1-nano-2025-04-14 OpenAI · Proprietary	1278±23	582
183	159198	qwen2-72b-instruct Alibaba · Qianwen LICENSE	1276±9	4,835
184	159197	gpt-4-0613 OpenAI · Proprietary	1276±8	11,183
185	163197	grok-2-mini-2024-08-13 xAI · Proprietary	1275±7	7,264
186	150208	llama-3.1-nemotron-51b-instruct Nvidia · Llama 3.1	1273±22	507
187	153207	qwen2.5-coder-32b-instruct Alibaba · Apache 2.0	1273±19	725
188	158204	deepseek-coder-v2 DeepSeek · DeepSeek License	1273±13	1,858
189	163202	amazon-nova-pro-v1.0 Amazon · Proprietary	1272±10	2,976
190	168201	llama-3.1-70b-instruct Meta · Llama 3.1 Community	1272±7	7,680
191	159206	gemma-3n-e4b-it Google · Gemma	1270±14	1,657
192	169206	phi-4 Microsoft · MIT	1267±10	2,756
193	156212	llama-3.1-tulu-3-70b Ai2 · Llama 3.1	1266±25	396
194	169208	mistral-small-24b-instruct-2501 Mistral · Apache 2.0	1264±13	1,677
195	172207	athene-70b-0725 NexusFlow · CC-BY-NC-4.0	1262±10	2,921
196	181208	llama-3-70b-instruct Meta · Llama 3 Community	1259±7	20,940
197	181208	gemini-1.5-flash-001 Google · Proprietary	1258±8	8,387
198	159220	gemma-3-4b-it Google · Gemma	1257±28	423
199	183209	claude-3-sonnet-20240229 Anthropic · Proprietary	1255±8	13,761
200	180210	nemotron-4-340b-instruct Nvidia · NVIDIA Open Model	1255±12	2,352
201	163225	hunyuan-standard-256k Tencent · Proprietary	1253±28	361
202	181219	glm-4-0520 Zhipu AI · Proprietary	1249±15	1,191
203	184219	reka-core-20240904 Reka AI · Proprietary	1248±14	1,207
204	185216	amazon-nova-lite-v1.0 Amazon · Proprietary	1248±11	2,510
205	184220	jamba-1.5-large AI21 Labs · Jamba Open	1247±15	1,147
206	189216	mistral-large-2402 Mistral · Proprietary	1246±9	7,987
207	190213	gemma-2-27b-it Google · Gemma license	1246±7	10,171
208	197231	reka-flash-20240904 Reka AI · Proprietary	1233±14	1,284
209	199225	c4ai-aya-expanse-32b Cohere · CC-BY-NC-4.0	1233±9	3,854
210	200225	claude-3-haiku-20240307 Anthropic · Proprietary	1232±7	14,985
211	198232	command-r-plus-08-2024 Cohere · CC-BY-NC-4.0	1232±14	1,467
212	201226	gemini-1.5-flash-8b-001 Google · Proprietary	1231±8	5,039
213	185244	olmo-2-0325-32b-instruct Ai2 · Apache-2.0	1230±28	375
214	201228	mixtral-8x22b-instruct-v0.1 Mistral · Apache 2.0	1230±9	6,777
215	201235	amazon-nova-micro-v1.0 Amazon · Proprietary	1227±11	2,454
216	203237	qwen1.5-110b-chat Alibaba · Qianwen LICENSE	1223±11	3,188
217	205237	mistral-medium Mistral · Proprietary	1223±11	4,406
218	199247	qwq-32b-preview Alibaba · Apache 2.0	1218±24	481
219	207238	gemma-2-9b-it Google · Gemma license	1218±7	7,111
220	207243	phi-3-medium-4k-instruct Microsoft · MIT	1217±10	3,238
221	203247	ministral-8b-2410 Mistral · MRL	1216±20	683
222	207243	yi-1.5-34b-chat 01 AI · Apache-2.0	1215±11	2,983
223	211243	command-r-plus Cohere · CC-BY-NC-4.0	1214±8	9,769
224	207247	reka-flash-21b-20240226-online Reka AI · Proprietary	1213±14	2,028
225	213246	qwen1.5-72b-chat Alibaba · Qianwen LICENSE	1210±9	5,325
226	210247	internlm2_5-20b-chat InternLM · Other	1209±15	1,388
227	203250	llama-3.1-tulu-3-8b Ai2 · Llama 3.1	1209±26	361
228	212247	command-r-08-2024 Cohere · CC-BY-NC-4.0	1207±13	1,601
229	212247	gemma-2-9b-it-simpo Princeton · MIT	1205±15	1,285
230	214247	gpt-3.5-turbo-1106 OpenAI · Proprietary	1203±15	2,134
231	215247	qwen1.5-32b-chat Alibaba · Qianwen LICENSE	1202±11	2,649
232	215248	c4ai-aya-expanse-8b Cohere · CC-BY-NC-4.0	1201±15	1,311
233	217247	reka-flash-21b-20240226 Reka AI · Proprietary	1200±11	3,363
234	218247	gpt-3.5-turbo-0125 OpenAI · Proprietary	1200±8	8,625
235	207256	granite-3.1-2b-instruct IBM · Apache 2.0	1200±26	393
236	214253	granite-3.0-8b-instruct IBM · Apache 2.0	1198±19	875
237	214254	gemini-pro Google · Proprietary	1198±19	993
238	212254	zephyr-orpo-141b-A35b-v0.1 HuggingFace · Apache 2.0	1197±22	589
239	218249	dbrx-instruct-preview Databricks · DBRX LICENSE	1197±11	4,002
240	218252	phi-3-mini-4k-instruct-june-2024 Microsoft · MIT	1195±13	1,568
241	218251	phi-3-small-8k-instruct Microsoft · MIT	1195±13	2,092
242	218252	gemini-pro-dev-api Google · Proprietary	1194±14	2,274
243	222248	llama-3-8b-instruct Meta · Llama 3 Community	1194±8	14,251
244	211262	granite-3.1-8b-instruct IBM · Apache 2.0	1193±28	385
245	222250	llama-3.1-8b-instruct Meta · Llama 3.1 Community	1193±8	7,137
246	222250	mixtral-8x7b-instruct-v0.1 Mistral · Apache 2.0	1193±8	9,662
247	221258	jamba-1.5-mini AI21 Labs · Jamba Open	1187±16	1,094
248	236260	command-r Cohere · CC-BY-NC-4.0	1176±9	6,684
249	233265	granite-3.0-2b-instruct IBM · Apache 2.0	1169±19	907
250	240264	qwen1.5-14b-chat Alibaba · Qianwen LICENSE	1169±13	2,184
251	239265	llama-3.2-3b-instruct Meta · Llama 3.2	1167±16	1,136
252	245265	snowflake-arctic-instruct Snowflake · Apache 2.0	1163±11	4,793
253	247264	gemma-2-2b-it Google · Gemma license	1163±8	6,603
254	245267	starling-lm-7b-beta Nexusflow · Apache-2.0	1161±14	1,973
255	243273	wizardlm-70b Microsoft · Llama 2 Community	1160±19	903
256	246267	openchat-3.5-0106 OpenChat · Apache-2.0	1159±13	1,726
257	247267	gemma-1.1-7b-it Google · Gemma license	1159±11	3,039
258	242274	deepseek-llm-67b-chat DeepSeek · DeepSeek License	1157±23	576
259	235281	smollm2-1.7b-instruct HuggingFace · Apache 2.0	1153±33	271
260	248273	yi-34b-chat 01 AI · Yi License	1153±13	2,044
261	249273	phi-3-mini-4k-instruct Microsoft · MIT	1152±12	2,563
262	246276	openhermes-2.5-mistral-7b NousResearch · Apache-2.0	1152±20	697
263	248279	tulu-2-dpo-70b AllenAI/UW · AI2 ImpACT Low-risk	1147±19	888
264	251279	phi-3-mini-128k-instruct Microsoft · MIT	1140±13	2,813
265	254279	llama-2-70b-chat Meta · Llama 2 Community	1138±10	4,740
266	257282	mistral-7b-instruct-v0.2 Mistral · Apache-2.0	1129±12	2,605
267	257283	starling-lm-7b-alpha UC Berkeley · CC-BY-NC-4.0	1128±16	1,300
268	249289	dolphin-2.2.1-mistral-7b Cognitive Computations · Apache-2.0	1126±32	219
269	257283	llama-3.2-1b-instruct Meta · Llama 3.2	1126±16	1,162
270	254285	qwen-14b-chat Alibaba · Qianwen LICENSE	1126±24	534
271	257283	openchat-3.5 OpenChat · Apache-2.0	1126±18	945
272	257285	qwen1.5-7b-chat Alibaba · Qianwen LICENSE	1122±20	690
273	262284	vicuna-33b LMSYS · Non-commercial	1117±12	2,663
274	261288	gemma-7b-it Google · Gemma license	1117±16	1,120
275	257290	llama2-70b-steerlm-chat Nvidia · Llama 2 Community	1117±27	440
276	260289	palm-2 Google · Proprietary	1114±19	901
277	265288	llama-2-13b-chat Meta · Llama 2 Community	1111±13	2,218
278	261290	solar-10.7b-instruct-v1.0 Upstage AI · CC-BY-NC-4.0	1111±22	604
279	262290	codellama-34b-instruct Meta · Llama 2 Community	1110±19	770
280	265290	gemma-1.1-2b-it Google · Gemma license	1106±16	1,355
281	262294	mpt-30b-chat MosaicML · CC-BY-NC-SA-4.0	1096±34	242
282	266292	nous-hermes-2-mixtral-8x7b-dpo NousResearch · Apache-2.0	1096±21	628
283	273292	llama-2-7b-chat Meta · Llama 2 Community	1088±14	1,656
284	271293	qwen1.5-4b-chat Alibaba · Qianwen LICENSE	1086±18	988
285	270294	stripedhyena-nous-7b Together AI · Apache 2.0	1086±20	676
286	273293	zephyr-7b-beta HuggingFace · MIT	1085±17	1,250
287	275292	vicuna-13b LMSYS · Llama 2 Community	1084±14	2,146
288	273294	mistral-7b-instruct Mistral · Apache 2.0	1082±19	974
289	267294	guanaco-33b UW · Non-commercial	1082±32	280
290	277294	gemma-2b-it Google · Gemma license	1069±22	596
291	281294	wizardlm-13b Microsoft · Llama 2 Community	1066±20	669
292	281294	olmo-7b-instruct Ai2 · Apache-2.0	1057±19	848
293	284295	vicuna-7b LMSYS · Llama 2 Community	1048±21	658
294	286295	chatglm3-6b Tsinghua · Apache-2.0	1043±23	576
295	293303	gpt4all-13b-snoozy Nomic AI · Non-commercial	998±37	211
296	295303	alpaca-13b Stanford · Non-commercial	989±23	652
297	295303	mpt-7b-chat MosaicML · CC-BY-NC-SA-4.0	984±25	471
298	295303	RWKV-4-Raven-14B RWKV · Apache 2.0	983±24	544
299	295303	koala-13b UC Berkeley · Non-commercial	981±21	751
300	295303	chatglm-6b Tsinghua · Non-commercial	978±25	525
301	295305	chatglm2-6b Tsinghua · Apache-2.0	972±35	227
302	295305	oasst-pythia-12b OpenAssistant · Apache 2.0	959±22	687
303	295306	dolly-v2-12b Databricks · MIT	948±29	370
304	301306	fastchat-t5-3b LMSYS · Apache 2.0	920±26	462
305	301306	llama-13b Meta · Non-commercial	917±33	252
306	303306	stablelm-tuned-alpha-7b Stability AI · CC-BY-NC-SA-4.0	891±29	353

Text Arena | Math

Default Leaderboard Plots

Battle Count for Each Combination of Models (without Ties)

Confidence Intervals on Model Strength (via Bootstrapping)

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)