LMArena Business and finance leaderboard

Full leaderboard

Rank	Model	Lab	Rating	95% interval	Votes	Price in / out
1	Gemini 4 Argon	Google	1512	1497–1527	1.7K	$2 / $10
2	Claude Opus 5	Anthropic	1501	1492–1509	6.4K	$5 / $25
3	Claude Opus 4.6	Anthropic	1497	1492–1503	16.3K	$5 / $25
5	Claude Opus 5.5	Anthropic	1497	1482–1511	1.8K	$4 / $20
7	Claude Fable 5.1	Anthropic	1492	1481–1503	2.9K	$10 / $50
8	Claude Opus 4.7	Anthropic	1490	1484–1497	13K	$5 / $25
9	Muse Spark 1.3	Meta	1489	1479–1499	3.7K	$1.25 / $4.25
10	Muse Spark 1.2	Meta	1484	1470–1498	1.9K	$1.25 / $4.25
11	Muse Wonder	Meta	1483	1465–1502	1K	$4 / $20
12	Qwen3.8-Max	Alibaba	1481	1473–1490	5.6K	$2 / $6
13	Gemini 3.7 Flash	Google	1480	1471–1488	5.5K	$0.75 / $3.75
14	Gemini 3.8 Flash	Google	1479	1472–1487	7.9K	$0.82 / $4.13
15	Claude Fable 5	Anthropic	1479	1472–1486	8.7K	$10 / $50
16	GPT-5.5	OpenAI	1478	1472–1485	13.7K	$5 / $30
18	GPT-5.4	OpenAI	1475	1468–1481	13.1K	$2.50 / $15
19	ERNIE 5.1	Baidu	1473	1466–1481	7.8K	—
21	Muse Spark 1.1	Meta	1470	1463–1477	8.7K	$1.25 / $4.25
22	Kimi K3	Moonshot AI	1469	1461–1477	6.6K	$0.24 / $11
23	MiMo-V2.6-Pro	Xiaomi	1469	1447–1491	715	$0.43 / $0.87
24	Claude Sonnet 5.5	Anthropic	1468	1453–1484	1.5K	$2 / $10
25	Gemini 3.5 Flash	Google	1467	1460–1474	9.4K	$1.50 / $9
26	MiMo-V2.5-Pro	Xiaomi	1466	1460–1472	14.9K	$0.30 / $0.61
27	Gemini 3.6 Flash	Google	1464	1456–1472	6.8K	$0.75 / $3.75
28	Claude Sonnet 4.6	Anthropic	1464	1458–1470	14.1K	$3 / $15
29	Qwen3.5-Max-Preview	Alibaba	1463	1454–1472	4.5K	—
30	Muse Spark	Meta	1462	1451–1474	2.9K	—
31	DeepSeek-V4.1-Flash-20260910	DeepSeek	1461	1449–1474	2.4K	$0.15 / $0.60
32	GLM-5.3-Flash	Z.ai	1461	1453–1469	7K	$0.15 / $0.50
33	Gemini 3.1 Pro Preview	Google	1459	1455–1464	25.3K	$2 / $12
34	GLM-5.3	Z.ai	1459	1450–1468	4.6K	$0.079 / $1.40
36	Gemini 3 Pro	Google	1458	1451–1465	7.7K	—
37	Claude Opus 4.8	Anthropic	1458	1452–1464	12.7K	$5 / $25
38	GPT-5.6 Sol	OpenAI	1457	1450–1465	7.8K	$4 / $20
41	GLM-5.1	Z.ai	1452	1446–1458	12.5K	$1.40 / $4.40
42	MiMo-V2.6-Flash	Xiaomi	1451	1439–1464	2.5K	$0.14 / $0.28
43	GLM-5.2	Z.ai	1451	1444–1458	9.9K	$0.034 / $7
44	amazon-nova-experimental-chat	Amazon	1450	1428–1472	637	—
45	Claude Opus 4.5	Anthropic	1448	1443–1454	14.1K	$5 / $25
46	GPT-6.1 Sol	OpenAI	1448	1431–1464	1.3K	$2 / $10
47	GPT-5.6 Terra	OpenAI	1448	1441–1455	8.6K	$2 / $12
48	Gemini 3 Flash	Google	1448	1439–1456	5.8K	$0.50 / $3
49	Qwen3.7-Max-Preview	Alibaba	1446	1426–1466	882	$1.48 / $4.42
50	Kimi K2.6	Moonshot AI	1445	1437–1452	7.9K	$0.65 / $3.41
51	DeepSeek-V4-Pro	DeepSeek	1443	1436–1450	11.4K	$0.66 / $1.98
53	Step 5 Preview	StepFun	1441	1426–1455	1.7K	$1 / $2.70
54	Grok 4.5	xAI	1441	1433–1448	7.6K	$2 / $6
55	Mistral Large 4	Mistral AI	1441	1427–1455	1.7K	$1.36 / $4.18
56	Claude Sonnet 4.5	Anthropic	1440	1435–1445	15.8K	$3 / $15
57	Gemini 2.5 Pro	Google	1440	1435–1444	22.8K	$1.25 / $10
58	GPT-5.6 Luna	OpenAI	1439	1432–1447	7.8K	$0.20 / $1.20
59	Dola Seed 2.0 Pro	ByteDance	1439	1433–1445	15.5K	—
60	IInkling	Thinky	1439	1432–1446	8.1K	$1 / $4.05
61	MiMo-V2-Pro	Xiaomi	1439	1430–1447	5K	—
62	GPT-6 Astra	OpenAI	1438	1426–1450	2.5K	$10 / $50
63	Qwen3.8-27B	Alibaba	1438	1429–1447	4.8K	$0.20 / $2.50
64	Claude Sonnet 5	Anthropic	1437	1430–1444	9.9K	$2 / $10
65	Qwen3-Max-Preview	Alibaba	1436	1428–1445	5.1K	—
66	NVIDIA-Nemotron-3-Ultra-550B-A55B	NVIDIA	1435	1422–1448	2.3K	—
67	Qwen3.7-Plus	Alibaba	1435	1428–1442	8.4K	$0.32 / $1.28
68	GLM-5V-Turbo	Z.ai	1435	1422–1448	2.1K	$1.20 / $4
69	Qwen3.5-397B-A17B	Alibaba	1435	1429–1440	19.1K	$0.50 / $3.60
70	MiniMax-M3	MiniMax	1434	1428–1440	12.9K	$0.30 / $1.20
72	Qwen3-VL-235B-A22B-Instruct	Alibaba	1433	1419–1447	2.2K	$0.21 / $1.90
73	GPT-5.2 Chat	OpenAI	1433	1425–1440	7K	$1.75 / $14
75	MiMo-V2.5	Xiaomi	1432	1425–1439	9.7K	$0.12 / $0.24
76	Grok 4.20 Beta	xAI	1432	1425–1438	13.4K	—
77	GPT-5.1	OpenAI	1431	1424–1438	7.7K	$1.25 / $10
78	Gemma 4 31B	Google	1430	1414–1447	1.2K	$0.20 / $0.40
79	Qwen3.6-Plus	Alibaba	1430	1423–1437	10.1K	$0.33 / $1.95
80	GLM-5	Z.ai	1430	1422–1438	5.9K	$1 / $3.20
81	BBeam 1.0 501B A23B	Reflection AI	1430	1408–1451	738	$0.25 / $1
82	MiMo-V2-Omni	Xiaomi	1430	1420–1439	4.2K	—
83	Gemma 4 26B A4B	Google	1429	1412–1446	1.1K	$0.068 / $0.23
84	GLM-4.7	Z.ai	1429	1417–1441	2.3K	$0.54 / $1.98
85	ERNIE 5.0	Baidu	1429	1422–1436	7K	—
86	LongCat-Flash-Chat Exp	Meituan	1428	1415–1441	2.1K	—
88	Qwen3.6-Max-Preview	Alibaba	1428	1410–1446	1.1K	—
89	Kimi K2.5	Moonshot AI	1427	1421–1433	14.4K	$0.50 / $2.50
90	Mistral Medium 3.5	Mistral AI	1426	1414–1439	2.3K	$1.50 / $7.50
92	ChatGPT-4o Latest	OpenAI	1425	1420–1431	13.6K	—
93	DeepSeek-V4-Flash	DeepSeek	1425	1418–1432	10.4K	$0.042 / $0.18
94	Grok 4.20 Beta 1	xAI	1425	1416–1433	5.4K	—
96	Hy3	Tencent	1424	1412–1436	2.5K	$0.083 / $0.33
97	Grok 4.1	xAI	1423	1417–1429	13.1K	—
98	Gemini 3.5 Flash-Lite	Google	1423	1415–1431	6.6K	$0.30 / $2.50
99	Grok 4.20 Multi-Agent Beta	xAI	1423	1416–1429	12.9K	—
101	Qwen3-Next-80B-A3B-Instruct	Alibaba	1422	1413–1431	4.3K	$0.09 / $1.10
103	GLM-4.5	Z.ai	1420	1411–1430	4.2K	$0.60 / $2.20
104	Qwen3-235B-A22B-Instruct	Alibaba	1418	1413–1423	18.3K	$0.09 / $0.55
105	Mistral Medium 3.1	Mistral AI	1418	1413–1423	17.9K	$0.40 / $2
106	Mistral Large 3	Mistral AI	1418	1412–1423	16.1K	$0.50 / $1.50
107	GPT-5.4 mini	OpenAI	1418	1411–1424	12.9K	$0.75 / $4.50
109	Grok 4.6	xAI	1417	1409–1425	5.9K	$2 / $6
111	DeepSeek-V3.1-Terminus	DeepSeek	1416	1394–1438	690	$0.27 / $1
112	GLM-4.6	Z.ai	1416	1409–1424	6.9K	$0.55 / $2.20
114	Qwen3.5-122B-A10B	Alibaba	1414	1406–1422	5.7K	$0.40 / $3.20
116	GPT-5.2	OpenAI	1414	1407–1421	9.8K	$1.75 / $14
117	Hunyuan Vision 1.5 Thinking	Tencent	1414	1387–1441	470	—
118	Qwen3-235B-A22B-Thinking	Alibaba	1413	1398–1428	1.5K	$0.45 / $3.50
119	IInkling-Small	Thinky	1412	1404–1421	6.5K	$0.45 / $1.20
120	DeepSeek-V3.2-Exp	DeepSeek	1412	1400–1425	2.2K	$0.28 / $0.42
122	GPT-5.5 Instant	OpenAI	1410	1402–1419	5.7K	—
123	Grok 3 Preview	xAI	1410	1400–1420	3.9K	—
127	DeepSeek-V3.1	DeepSeek	1409	1396–1423	1.9K	$0.25 / $0.95
128	MiniMax-M2.7	MiniMax	1407	1402–1413	16.8K	$0.30 / $1.20
129	Claude Haiku 5.5	Anthropic	1406	1387–1424	1K	$0.10 / $0.50
130	Claude Opus 4.1	Anthropic	1405	1400–1411	14.1K	$15 / $75
133	Muse Glimmer	Meta	1405	1383–1427	728	—
135	Gemini 2.5 Flash	Google	1404	1399–1408	22.7K	$0.30 / $2.50
136	MiMo-V2-Flash	Xiaomi	1402	1396–1409	9.2K	—
137	DeepSeek-R1	DeepSeek	1401	1390–1413	2.9K	$0.50 / $2.15
139	NVIDIA-Nemotron-3.5-Super-VL-120B-A12B	NVIDIA	1400	1377–1423	651	—
140	Claude Haiku 4.5	Anthropic	1400	1396–1405	29.3K	$1 / $5
141	GPT-5 Chat	OpenAI	1399	1391–1408	5.6K	—
142	Qwen3.5-27B	Alibaba	1399	1390–1407	5.6K	$0.27 / $2.16
146	Kimi K2 Thinking Turbo	Moonshot AI	1397	1392–1403	12.1K	—
149	Qwen3.5-Flash	Alibaba	1395	1388–1401	12.2K	$0.065 / $0.26
150	Grok 4 Fast	xAI	1394	1384–1404	3.6K	—
151	Step-3.5-Flash	StepFun	1394	1388–1400	11.8K	$0.10 / $0.30
152	Qwen3.5-35B-A3B	Alibaba	1394	1386–1401	6.1K	$0.14 / $1
153	o3	OpenAI	1393	1386–1399	9.5K	$2 / $8
154	Qwen3-235B-A22B	Alibaba	1392	1384–1400	6.3K	$0.09 / $0.55
155	Qwen3-VL-235B-A22B-Thinking	Alibaba	1391	1376–1405	1.6K	—
156	MiniMax-M2.1 Preview	MiniMax	1390	1379–1400	3.2K	$0.30 / $1.20
157	Gemini 3.1 Flash-Lite Preview	Google	1389	1383–1395	12.6K	$0.25 / $1.50
158	Qwen3-30B-A3B-Instruct	Alibaba	1389	1380–1398	4.1K	$0.09 / $0.30
159	Grok 4.7	xAI	1388	1376–1400	2.5K	$2 / $6
160	Grok 4	xAI	1388	1381–1395	7.1K	—
162	GPT-6 Luna	OpenAI	1387	1381–1394	12.4K	$0.10 / $0.50
163	GPT-4.5 Preview	OpenAI	1386	1370–1401	1.4K	—
165	Hunyuan TurboS	Tencent	1385	1369–1401	1.4K	—
166	GPT-5.3 Chat	OpenAI	1384	1376–1392	6.8K	—
167	Grok 4.1 Fast	xAI	1384	1378–1390	11K	—
169	GPT-6 Sol	OpenAI	1381	1369–1393	2.7K	$2 / $10
170	Grok 4.3	xAI	1381	1375–1387	14.2K	$1.25 / $2.50
171	Solar Pro 4	Upstage	1381	1371–1390	4.4K	$0.15 / $0.60
172	GPT-5	OpenAI	1377	1369–1386	5.5K	$1.25 / $10
174	Gemma 3 12B IT	Google	1376	1346–1406	364	$0.05 / $0.15
175	Hunyuan T1	Tencent	1372	1351–1393	761	—
176	GLM-4.5-Air	Z.ai	1370	1362–1378	5.5K	$0.13 / $0.85
177	GPT-4.1	OpenAI	1369	1362–1376	8.2K	$2 / $8
178	Amazon Nova 2 Lite	Amazon	1369	1356–1381	2.3K	—
179	Gemini 2.5 Flash-Lite Preview	Google	1367	1361–1374	9.1K	$0.10 / $0.40
180	GPT-5.4 nano	OpenAI	1366	1360–1373	12.6K	$0.20 / $1.25
181	NVIDIA-Nemotron-3-Super-120B-A12B	NVIDIA	1364	1349–1379	1.5K	—
182	Qwen3-Next-80B-A3B-Thinking	Alibaba	1360	1348–1372	2.5K	$0.15 / $1.20
183	Gemma 3 27B IT	Google	1359	1352–1367	6.5K	$0.08 / $0.35
184	GLM-4.6V	Z.ai	1359	1334–1384	551	$0.30 / $0.90
185	gpt-oss-120b	OpenAI	1359	1350–1367	5.4K	$0.15 / $0.60
186	GPT-5 mini	OpenAI	1358	1349–1367	4.8K	$0.25 / $2
187	LLing-flash-2.0	Ant Group	1357	1341–1373	1.3K	—
188	MiniMax-M2.5	MiniMax	1357	1349–1364	8.4K	$0.30 / $1.20
190	Kimi K2 Preview	Moonshot AI	1354	1341–1367	2K	$0.60 / $2.50
191	Mistral Medium 3	Mistral AI	1352	1343–1360	5.1K	$0.40 / $2
193	Mercury 2	Inception	1349	1325–1374	512	$0.25 / $0.75
194	Qwen2.5-Max	Alibaba	1349	1339–1359	3.7K	—
195	DeepSeek-V3	DeepSeek	1349	1342–1357	6.9K	$0.29 / $1.14
196	IINTELLECT-3	—	1348	1330–1367	1K	—
198	Grok 3 Mini Beta	xAI	1347	1337–1357	3.3K	—
199	Granite 4.2 30B	IBM	1346	1322–1371	632	—
200	NVIDIA-Nemotron-3-Nano-30B-A3B	NVIDIA	1346	1335–1356	3K	—
201	Claude Opus 4	Anthropic	1344	1336–1352	6K	—
202	Grok 3 Mini	xAI	1344	1332–1355	2.6K	—
203	Qwen3-Coder-480B-A35B-Instruct	Alibaba	1343	1334–1353	4.4K	—
204	GLM-4.7-Flash	Z.ai	1343	1331–1355	2.2K	$0.06 / $0.40
206	Step-3	StepFun	1343	1326–1359	1.1K	—
208	Gemini 2.0 Flash	Google	1336	1328–1345	5.3K	—
209	MiniMax-M2	MiniMax	1336	1319–1352	1.3K	$0.26 / $1.02
210	Gemini 2.0 Flash-Lite Preview	Google	1335	1323–1347	2.4K	—
211	Trinity Large Thinking	Arcee	1329	1321–1338	6.1K	$0.25 / $0.80
212	RRing-flash-2.0	Ant Group	1329	1313–1345	1.3K	—
213	Step-1o Turbo	StepFun	1329	1313–1344	1.4K	—
214	o1	OpenAI	1328	1316–1339	2.7K	$15 / $60
215	Trinity Large Preview	Arcee	1327	1319–1335	6K	—
216	GLM-4-Plus	Z.ai	1326	1303–1350	592	—
217	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	NVIDIA	1325	1315–1336	4.1K	—
218	Mistral Small 3.2	Mistral AI	1325	1314–1336	2.9K	—
219	o4-mini	OpenAI	1325	1317–1332	7K	$1.10 / $4.40
221	Granite 4.2 8B	IBM	1322	1297–1347	607	$0.06 / $0.25
222	GPT-4.1 mini	OpenAI	1322	1314–1330	6K	$0.40 / $1.60
223	QwQ-32B	Alibaba	1320	1310–1330	3.5K	—
224	MiniMax-M1	MiniMax	1319	1311–1327	6K	$0.55 / $2.20
225	Claude Sonnet 4	Anthropic	1318	1310–1326	6.5K	—
226	Qwen3-32B	Alibaba	1318	1292–1344	437	$0.08 / $0.28
227	Olmo 3.1 32B Instruct	Ai2	1318	1305–1330	2.1K	—
228	Command A	Cohere	1315	1308–1321	8.8K	$0.30 / $1.50
230	o3-mini	OpenAI	1313	1299–1327	1.8K	$1.10 / $4.40
231	Llama 3.3 Nemotron Super 49B v1.5	NVIDIA	1311	1288–1334	595	—
232	Gemma 3 4B IT	Google	1311	1281–1341	390	$0.04 / $0.05
233	GPT-5 nano	OpenAI	1311	1295–1326	1.5K	$0.05 / $0.40
234	GLM-4.5V	Z.ai	1309	1290–1328	906	$0.60 / $1.80
235	Hunyuan Turbo	Tencent	1309	1275–1342	256	—
236	Qwen3-30B-A3B	Alibaba	1308	1299–1318	4K	$0.12 / $0.50
239	Qwen-Plus	Alibaba	1303	1280–1326	571	$0.26 / $0.78
240	Llama 3.1 Nemotron Ultra 253B v1	NVIDIA	1301	1267–1335	254	—
241	Gemma 3n E4B IT	Google	1295	1285–1306	3.3K	—
242	Olmo 3 32B Think	Ai2	1290	1272–1308	1.1K	—
243	Mercury	Inception	1290	1259–1322	359	—
245	Qwen2.5-Plus	Alibaba	1289	1271–1306	1.1K	—
246	Granite 4.2 3B	IBM	1288	1262–1313	641	—
247	o1-mini	OpenAI	1287	1278–1295	6.1K	—
248	Llama 3.3 Nemotron Super 49B v1	NVIDIA	1286	1252–1321	241	—
249	Gemini 1.5 Pro	Google	1286	1278–1294	6.4K	—
250	gpt-oss-20b	OpenAI	1283	1269–1298	1.8K	$0.018 / $0.09
251	Step-2 16K Exp	StepFun	1283	1258–1308	506	—
252	AAthene V2 Chat	—	1274	1262–1285	2.7K	—
254	Claude 3.7 Sonnet	Anthropic	1273	1264–1281	5.8K	—
255	Yi Lightning	01.AI	1271	1260–1282	3.4K	—
257	Granite 4.1 8B	IBM	1268	1244–1291	698	—
258	GPT-4.1 nano	OpenAI	1267	1245–1288	651	$0.10 / $0.40
259	Grok 2	xAI	1265	1257–1273	7.5K	—
260	GPT-4o mini	OpenAI	1265	1257–1273	7.8K	$0.15 / $0.60
261	Gemini 1.5 Flash	Google	1264	1255–1274	4.3K	—
262	Llama 3.1 Nemotron 70B Instruct	NVIDIA	1262	1243–1281	904	—
263	GPT-4o	OpenAI	1262	1254–1269	13.3K	$2.50 / $10
264	Llama 4 Maverick 17B 128E Instruct	Meta	1260	1252–1268	6.1K	—
265	DeepSeek-V2.5	DeepSeek	1259	1238–1281	715	—
266	Mistral Small 3.1 24B Instruct	Mistral AI	1257	1249–1266	5.5K	$0.35 / $0.56
267	Llama 4 Scout 17B 16E Instruct	Meta	1257	1248–1266	4.9K	—
268	Qwen-Max	Alibaba	1256	1243–1269	2.2K	—
269	Claude 3.5 Sonnet	Anthropic	1255	1249–1261	11.3K	—
270	Hunyuan Standard	Tencent	1255	1226–1284	376	—
271	Grok 2 mini	xAI	1254	1245–1262	6.1K	—
272	Qwen2.5-72B-Instruct	Alibaba	1253	1244–1262	4.7K	$0.36 / $0.40
273	Olmo 3.1 32B Think	Ai2	1253	1236–1269	1.5K	—
276	Llama 3.1 405B Instruct	Meta	1247	1239–1256	6.7K	—
277	Gemini Advanced	Google	1246	1236–1257	6.1K	—
278	AAthene 70B	—	1246	1232–1259	2.1K	—
280	Llama 3.3 70B Instruct	Meta	1243	1235–1250	6.6K	$0.10 / $0.32
281	Hunyuan Large	Tencent	1241	1210–1272	357	—
282	Mistral Large	Mistral AI	1238	1227–1249	3K	$0.50 / $1.50
283	Llama 3.1 70B Instruct	Meta	1235	1227–1244	6.4K	$0.40 / $0.40
286	Amazon Nova Pro 1.0	Amazon	1229	1218–1240	2.6K	—
287	Hunyuan Large Vision	Tencent	1226	1205–1248	780	—
288	Llama 3.1 Tulu 3 70B	Ai2	1226	1194–1258	288	—
289	Mistral Large 2	Mistral AI	1226	1217–1235	5.2K	—
291	Qwen2.5-Coder-32B-Instruct	Alibaba	1224	1202–1246	629	$0.66 / $1
292	Magistral Medium	Mistral AI	1223	1209–1236	2.2K	—
293	Claude 3.5 Haiku	Anthropic	1223	1216–1229	9.1K	—
294	GPT-4 Turbo	OpenAI	1222	1214–1231	10.8K	$10 / $30
295	Gemma 2 9B IT SimPO	Google	1222	1205–1239	1.1K	—
296	Claude 3 Opus	Anthropic	1222	1215–1229	21.7K	—
297	Amazon Nova Lite 1.0	Amazon	1219	1206–1232	2.1K	—
298	Reka Core	Reka	1217	1198–1237	837	—
300	Llama 3.1 Nemotron 51B Instruct	NVIDIA	1215	1189–1242	421	—
301	Command R+	Cohere	1215	1198–1232	1.1K	$0.15 / $0.60
302	Granite-4.0-H-Small	IBM	1213	1193–1232	1.1K	—
304	Gemini 1.5 Flash-8B	Google	1211	1201–1221	4.3K	—
305	Aya Expanse 32B	Cohere	1210	1199–1221	3.1K	—
306	Gemma 2 27B IT	Google	1208	1200–1215	8.7K	$0.65 / $0.65
307	Mistral Small 24B Instruct	Mistral AI	1205	1190–1221	1.4K	$0.05 / $0.08
308	Phi-4	Microsoft	1199	1187–1211	2.4K	$0.07 / $0.14
309	Llama 3.1 Tulu 3 8B	Ai2	1196	1165–1228	285	—
310	Jamba 1.5 Large	AI21 Labs	1196	1178–1215	979	—
311	Reka Flash	Reka	1191	1173–1210	904	—
313	Gemma 2 9B IT	Google	1190	1181–1198	6.2K	—
314	Nemotron-4 340B Instruct	NVIDIA	1185	1172–1198	2.2K	—
315	Amazon Nova Micro 1.0	Amazon	1182	1169–1195	2.1K	—
316	OLMo 2 32B Instruct	Ai2	1181	1149–1213	336	—
317	Hunyuan Standard 256K	Tencent	1178	1147–1209	328	—
318	GLM-4	Z.ai	1177	1159–1194	1.2K	—
319	Aya Expanse 8B	Cohere	1176	1158–1194	1.1K	—
320	Claude 3 Sonnet	Anthropic	1174	1165–1183	11.9K	—
321	Ministral 8B	Mistral AI	1173	1149–1196	572	$0.15 / $0.15
322	Llama 3 70B Instruct	Meta	1172	1164–1180	16.6K	—
323	Llama 3.1 8B Instruct	Meta	1166	1157–1175	5.7K	$0.05 / $0.08
324	Claude 3 Haiku	Anthropic	1158	1149–1166	13.2K	—
325	Jamba 1.5 Mini	AI21 Labs	1157	1139–1176	1K	—
327	DeepSeek-Coder-V2	DeepSeek	1155	1141–1170	1.8K	—
328	Qwen2-72B-Instruct	Alibaba	1146	1136–1157	4.3K	—
329	GPT-4	OpenAI	1145	1134–1156	5.1K	$30 / $60
330	Granite 3.1 8B Instruct	IBM	1142	1109–1175	316	—
332	Qwen1.5-110B-Chat	Alibaba	1140	1128–1153	3.1K	—
333	Granite 3.1 2B Instruct	IBM	1139	1110–1168	382	—
334	Reka Flash 21B	Reka	1135	1120–1151	1.7K	—
335	Yi 1.5 34B Chat	01.AI	1135	1122–1147	2.8K	—
336	Gemini Pro	Google	1131	1114–1148	1.7K	$2 / $10
338	Llama 3 8B Instruct	Meta	1127	1118–1136	10.8K	—
340	Gemma 2 2B IT	Google	1126	1116–1135	5.2K	—
342	Mistral Medium	Mistral AI	1119	1107–1132	3.2K	—
343	Mixtral 8x22B Instruct v0.1	Mistral AI	1119	1108–1129	5.6K	—
344	Qwen1.5-72B-Chat	Alibaba	1117	1105–1129	3.8K	—
345	IInternLM2.5 20B Chat	—	1115	1098–1132	1.3K	—
346	SStarling LM 7B Beta	—	1104	1088–1120	1.7K	—
347	Phi-3 Medium 4K Instruct	Microsoft	1099	1087–1111	2.8K	—
349	Qwen1.5-32B-Chat	Alibaba	1094	1081–1108	2.3K	—
350	ZZephyr ORPO 141B A35B v0.1	—	1089	1061–1117	441	—
351	Yi 34B Chat	01.AI	1089	1072–1105	1.4K	—
352	Mixtral 8x7B Instruct v0.1	Mistral AI	1084	1074–1093	7.1K	—
354	Qwen1.5-14B-Chat	Alibaba	1083	1067–1098	1.9K	—
355	Llama 2 70B Chat	Meta	1083	1071–1095	3.5K	—
356	WizardLM 70B	Microsoft	1078	1055–1102	682	—
357	Llama 2 70B SteerLM Chat	NVIDIA	1078	1043–1113	282	—
358	TTulu 2 DPO 70B	—	1077	1052–1103	540	—
359	Phi-3 Small 8K Instruct	Microsoft	1077	1063–1091	2.2K	—
360	GPT-3.5 Turbo	OpenAI	1076	1066–1086	6.9K	$1 / $2
361	OOpenChat 3.5	—	1074	1056–1092	1.2K	—
362	Llama 3.2 3B Instruct	Meta	1074	1054–1093	1K	$0.051 / $0.34
363	SStarling LM 7B Alpha	—	1073	1052–1093	841	—
364	DDBRX Instruct Preview	—	1072	1059–1085	3.4K	—
365	Nous Hermes 2 Mixtral 8x7B DPO	Nous Research	1071	1037–1106	282	—
366	Qwen1.5-7B-Chat	Alibaba	1064	1036–1091	447	—
367	Gemma 1.1 7B IT	Google	1063	1050–1076	2.7K	—
368	Llama 2 13B Chat	Meta	1056	1040–1072	1.7K	—
369	VVicuna 33B	—	1054	1039–1070	1.9K	—
370	DeepSeek LLM 67B Chat	DeepSeek	1048	1019–1076	441	—
371	Granite 3.0 8B Instruct	IBM	1041	1018–1063	813	—
372	Mistral 7B Instruct v0.2	Mistral AI	1038	1023–1054	1.7K	—
374	Granite 3.0 2B Instruct	IBM	1035	1014–1057	873	—
375	Code Llama 34B Instruct	Meta	1034	1009–1058	639	—
376	Phi-3 Mini 4K Instruct	Microsoft	1032	1019–1046	2.5K	—
377	Snowflake Arctic Instruct	Snowflake	1031	1018–1045	3.3K	—
378	Llama 2 7B Chat	Meta	1028	1010–1046	1.3K	—
379	Gemma 7B IT	Google	1025	1003–1046	818	—
380	OpenHermes 2.5 Mistral 7B	Mistral AI	1024	995–1054	381	—
382	SOLAR 10.7B Instruct v1.0	Upstage	1020	986–1054	311	—
384	OLMo 7B Instruct	Ai2	1020	994–1046	548	—
385	MMPT 30B Chat	—	1008	971–1046	207	—
386	WizardLM 13B	Microsoft	1006	982–1031	634	—
387	VVicuna 13B	—	1006	989–1023	1.6K	—
388	Qwen-14B-Chat	Alibaba	1001	973–1030	426	—
389	ZZephyr 7B Beta	—	1000	980–1021	997	—
390	Llama 3.2 1B Instruct	Meta	1000	979–1020	1K	$0.027 / $0.20
391	Gemma 2B IT	Google	999	971–1027	447	—
392	Phi-3 Mini 128K Instruct	Microsoft	990	974–1006	2.1K	—
393	Gemma 1.1 2B IT	Google	981	962–1000	1.1K	—
394	GGuanaco 33B	—	973	934–1011	261	—
395	VVicuna 7B	—	973	945–1000	555	—
396	SStripedHyena Nous 7B	—	970	941–999	455	—
397	SSmolLM2 1.7B Instruct	—	965	922–1008	252	—
398	Qwen1.5-4B-Chat	Alibaba	965	941–988	738	—
399	PaLM 2	Google	959	935–983	755	—
400	Mistral 7B Instruct	Mistral AI	952	929–976	747	—
401	KKoala 13B	—	936	907–966	503	—
402	CChatGLM3 6B	—	931	900–963	378	—
403	RRWKV-4 Raven 14B	—	888	855–922	360	—
404	CChatGLM2 6B	—	887	846–928	234	—
405	FFastChat-T5 3B	—	868	830–907	287	—
406	MMPT 7B Chat	—	864	828–901	306	—
407	CChatGLM 6B	—	846	808–883	300	—
408	OOpenAssistant Pythia 12B	—	822	792–852	454	—
409	AAlpaca 13B	—	812	779–846	391	—
410	SStableLM Tuned Alpha 7B	—	786	746–827	238	—
411	DDolly 2.0 12B	—	734	690–778	233	—

Show all 344 models

LMArena ranks overlap where confidence intervals do, so several models can share a rank. Where a model is rated at several effort levels, its best is shown.

Related leaderboards

• LMArena Legal and government
• LMArena Medicine and healthcare