LMArena Expert leaderboard

Full leaderboard

Rank	Model	Lab	Rating	95% interval	Votes	Price in / out
1	Claude Opus 5	Anthropic	1553	1545–1561	7.9K	$5 / $25
3	Claude Opus 5.5	Anthropic	1550	1532–1569	1.1K	$4 / $20
4	Gemini 4 Argon	Google	1545	1527–1564	1K	$2 / $10
5	Claude Fable 5.1	Anthropic	1545	1528–1561	1.4K	$10 / $50
6	Claude Opus 4.6	Anthropic	1543	1536–1551	7.6K	$5 / $25
7	MiMo-V2.6-Pro	Xiaomi	1541	1514–1567	464	$0.43 / $0.87
9	Claude Fable 5	Anthropic	1534	1525–1543	4.9K	$10 / $50
10	Claude Sonnet 5.5	Anthropic	1530	1511–1549	924	$2 / $10
11	Gemini 3.8 Flash	Google	1527	1518–1536	5.1K	$0.82 / $4.13
12	Claude Opus 4.7	Anthropic	1521	1513–1529	7.1K	$5 / $25
13	Kimi K3	Moonshot AI	1520	1509–1531	3.2K	$0.24 / $11
15	GPT-5.6 Sol	OpenAI	1516	1507–1525	4.8K	$4 / $20
16	Muse Spark 1.3	Meta	1515	1503–1528	2.2K	$1.25 / $4.25
17	Muse Wonder	Meta	1514	1491–1537	622	$4 / $20
18	Gemini 3.7 Flash	Google	1514	1503–1524	3.5K	$0.75 / $3.75
19	GLM-5.3	Z.ai	1514	1501–1526	2.4K	$0.079 / $1.40
20	GLM-5.3-Flash	Z.ai	1512	1502–1522	3.9K	$0.15 / $0.50
21	GPT-5.5	OpenAI	1507	1500–1515	7.4K	$5 / $30
22	GPT-5.4	OpenAI	1507	1498–1515	6.4K	$2.50 / $15
23	Qwen3.8-Max	Alibaba	1507	1496–1517	3.3K	$2 / $6
24	amazon-nova-experimental-chat	Amazon	1506	1474–1538	304	—
26	Claude Opus 4.8	Anthropic	1503	1495–1510	7.1K	$5 / $25
27	DeepSeek-V4.1-Flash-20260910	DeepSeek	1502	1487–1517	1.5K	$0.15 / $0.60
28	MiMo-V2.5-Pro	Xiaomi	1501	1493–1508	7.6K	$0.30 / $0.61
29	Claude Sonnet 4.6	Anthropic	1500	1493–1508	7.4K	$3 / $15
30	GPT-5.6 Terra	OpenAI	1496	1487–1505	5.4K	$2 / $12
31	MiMo-V2.6-Flash	Xiaomi	1495	1479–1511	1.4K	$0.14 / $0.28
32	Gemini 3.5 Flash	Google	1494	1486–1503	5.6K	$1.50 / $9
33	GPT-6 Astra	OpenAI	1492	1476–1509	1.4K	$10 / $50
35	ERNIE 5.1	Baidu	1491	1481–1502	3.7K	—
36	Claude Sonnet 5	Anthropic	1490	1482–1499	5.7K	$2 / $10
37	Kimi K2.6	Moonshot AI	1490	1481–1500	3.9K	$0.65 / $3.41
38	Gemini 3.6 Flash	Google	1490	1480–1499	4.2K	$0.75 / $3.75
39	GPT-6.1 Sol	OpenAI	1489	1469–1510	759	$2 / $10
40	Qwen3.5-Max-Preview	Alibaba	1489	1476–1501	2.2K	—
41	Qwen3.7-Max-Preview	Alibaba	1488	1457–1519	392	$1.48 / $4.42
42	GLM-5.2	Z.ai	1487	1479–1496	5.5K	$0.034 / $7
43	Claude Opus 4.5	Anthropic	1487	1479–1496	5.7K	$5 / $25
45	Gemini 3.1 Pro Preview	Google	1483	1477–1490	13.6K	$2 / $12
46	Claude Sonnet 4.5	Anthropic	1482	1474–1490	6.1K	$3 / $15
49	Qwen3.8-27B	Alibaba	1480	1468–1491	2.9K	$0.20 / $2.50
50	GLM-5.1	Z.ai	1478	1471–1486	7K	$1.40 / $4.40
51	GPT-5.6 Luna	OpenAI	1478	1469–1487	4.7K	$0.20 / $1.20
52	Muse Spark 1.1	Meta	1478	1469–1486	5.4K	$1.25 / $4.25
53	MiMo-V2-Pro	Xiaomi	1477	1464–1490	2.2K	—
54	Qwen3.6-Max-Preview	Alibaba	1477	1452–1502	556	—
55	Step 5 Preview	StepFun	1477	1458–1495	981	$1 / $2.70
56	Gemini 3 Pro	Google	1475	1464–1487	2.8K	—
57	Muse Spark 1.2	Meta	1474	1456–1492	1.1K	$1.25 / $4.25
59	NVIDIA-Nemotron-3-Ultra-550B-A55B	NVIDIA	1472	1455–1489	1.2K	—
60	GPT-5.1	OpenAI	1470	1458–1482	2.6K	$1.25 / $10
61	Grok 4.6	xAI	1468	1457–1478	3.7K	$2 / $6
62	Qwen3.7-Plus	Alibaba	1467	1458–1476	4.7K	$0.32 / $1.28
63	IInkling	Thinky	1466	1457–1475	5.1K	$1 / $4.05
64	Kimi K2.5	Moonshot AI	1466	1458–1473	7K	$0.50 / $2.50
65	Grok 4.5	xAI	1465	1455–1474	4.7K	$2 / $6
66	Gemma 4 31B	Google	1465	1440–1489	501	$0.20 / $0.40
67	Qwen3-235B-A22B-Thinking	Alibaba	1463	1435–1491	423	$0.45 / $3.50
68	DeepSeek-V4-Pro	DeepSeek	1463	1454–1471	5.9K	$0.66 / $1.98
69	Gemini 3 Flash	Google	1463	1450–1475	2.2K	$0.50 / $3
70	Qwen3.5-397B-A17B	Alibaba	1462	1455–1468	10.4K	$0.50 / $3.60
71	Hy3	Tencent	1461	1446–1477	1.4K	$0.083 / $0.33
72	MiniMax-M3	MiniMax	1461	1454–1469	7.3K	$0.30 / $1.20
74	MiMo-V2.5	Xiaomi	1459	1450–1468	4.8K	$0.12 / $0.24
75	Muse Spark	Meta	1457	1441–1473	1.4K	—
76	Qwen3-Max-Preview	Alibaba	1455	1439–1471	1.3K	—
77	Qwen3.6-Plus	Alibaba	1454	1445–1463	4.9K	$0.33 / $1.95
78	LongCat-Flash-Chat Exp	Meituan	1454	1443–1465	2.8K	—
79	GLM-5	Z.ai	1454	1443–1466	2.6K	$1 / $3.20
80	GLM-5V-Turbo	Z.ai	1454	1437–1470	1.2K	$1.20 / $4
81	Gemini 2.5 Pro	Google	1452	1445–1459	8.3K	$1.25 / $10
82	Mistral Large 4	Mistral AI	1449	1431–1467	1.1K	$1.36 / $4.18
84	MiMo-V2-Omni	Xiaomi	1449	1436–1462	2.1K	—
85	Claude Haiku 5.5	Anthropic	1448	1425–1471	617	$0.10 / $0.50
86	BBeam 1.0 501B A23B	Reflection AI	1447	1419–1476	387	$0.25 / $1
87	Gemma 4 26B A4B	Google	1447	1421–1472	454	$0.068 / $0.23
88	Grok 4.20 Multi-Agent Beta	xAI	1446	1438–1454	6.5K	—
90	GPT-5.2	OpenAI	1445	1435–1455	4K	$1.75 / $14
92	Claude Haiku 4.5	Anthropic	1443	1438–1449	14.1K	$1 / $5
93	MiniMax-M2.7	MiniMax	1443	1436–1450	8.8K	$0.30 / $1.20
94	Qwen3-VL-235B-A22B-Instruct	Alibaba	1442	1418–1466	596	$0.21 / $1.90
95	Qwen3-235B-A22B-Instruct	Alibaba	1442	1434–1449	6.5K	$0.09 / $0.55
97	DeepSeek-V4-Flash	DeepSeek	1441	1432–1450	5.4K	$0.042 / $0.18
99	IInkling-Small	Thinky	1440	1430–1450	4.1K	$0.45 / $1.20
100	Dola Seed 2.0 Pro	ByteDance	1440	1432–1447	7.8K	—
101	Grok 4.7	xAI	1439	1423–1455	1.4K	$2 / $6
102	Grok 4.20 Beta	xAI	1439	1431–1447	6.7K	—
103	Kimi K2 Thinking Turbo	Moonshot AI	1439	1430–1448	4.7K	—
104	GPT-6 Luna	OpenAI	1439	1431–1447	7.5K	$0.10 / $0.50
105	Claude Opus 4.1	Anthropic	1439	1427–1450	2.5K	$15 / $75
106	GPT-5.2 Chat	OpenAI	1438	1427–1448	3.2K	$1.75 / $14
107	DeepSeek-V3.2-Exp	DeepSeek	1436	1426–1446	3.4K	$0.28 / $0.42
109	GPT-6 Sol	OpenAI	1436	1420–1451	1.5K	$2 / $10
110	GPT-5.4 mini	OpenAI	1435	1427–1443	6.3K	$0.75 / $4.50
111	NVIDIA-Nemotron-3.5-Super-VL-120B-A12B	NVIDIA	1434	1407–1461	451	—
112	Gemini 3.5 Flash-Lite	Google	1433	1424–1443	4.2K	$0.30 / $2.50
113	GLM-4.5	Z.ai	1433	1416–1450	1.2K	$0.60 / $2.20
114	GLM-4.6	Z.ai	1432	1419–1445	2.1K	$0.55 / $2.20
115	Mistral Medium 3.5	Mistral AI	1432	1415–1449	1.2K	$1.50 / $7.50
116	Qwen3.5-122B-A10B	Alibaba	1431	1420–1443	2.7K	$0.40 / $3.20
119	MiniMax-M2.1 Preview	MiniMax	1431	1414–1447	1.2K	$0.30 / $1.20
120	Qwen3-VL-235B-A22B-Thinking	Alibaba	1429	1400–1458	412	—
122	Solar Pro 4	Upstage	1428	1416–1440	2.8K	$0.15 / $0.60
123	Qwen3.5-27B	Alibaba	1428	1416–1439	2.7K	$0.27 / $2.16
124	ERNIE 5.0	Baidu	1427	1416–1438	3K	—
125	Grok 4.20 Beta 1	xAI	1427	1415–1439	2.5K	—
126	Gemini 2.5 Flash	Google	1426	1419–1433	8.4K	$0.30 / $2.50
128	MiMo-V2-Flash	Xiaomi	1425	1416–1435	4K	—
129	GLM-4.7	Z.ai	1423	1403–1444	808	$0.54 / $1.98
133	Mistral Large 3	Mistral AI	1422	1415–1429	8.3K	$0.50 / $1.50
134	Step-3.5-Flash	StepFun	1422	1413–1430	5.3K	$0.10 / $0.30
135	Grok 3 Preview	xAI	1421	1406–1436	1.6K	—
137	GPT-5	OpenAI	1419	1404–1434	1.7K	$1.25 / $10
140	Grok 4.1	xAI	1418	1409–1426	4.9K	—
141	Qwen3-Next-80B-A3B-Instruct	Alibaba	1417	1399–1434	1.1K	$0.09 / $1.10
142	Grok 4	xAI	1415	1402–1428	2.1K	—
143	Grok 4 Fast	xAI	1412	1393–1431	943	—
145	GPT-5.5 Instant	OpenAI	1409	1397–1421	2.8K	—
146	Mistral Medium 3.1	Mistral AI	1408	1401–1416	6.6K	$0.40 / $2
147	Qwen3.5-Flash	Alibaba	1407	1399–1416	5.8K	$0.065 / $0.26
148	Qwen3.5-35B-A3B	Alibaba	1407	1396–1418	2.8K	$0.14 / $1
150	DeepSeek-V3.1	DeepSeek	1405	1380–1430	538	$0.25 / $0.95
151	Granite 4.2 30B	IBM	1405	1375–1435	372	—
154	GPT-5 Chat	OpenAI	1403	1388–1418	1.5K	—
155	o3	OpenAI	1402	1391–1413	3K	$2 / $8
157	ChatGPT-4o Latest	OpenAI	1401	1392–1410	4.6K	—
158	Gemini 3.1 Flash-Lite Preview	Google	1399	1390–1407	6.2K	$0.25 / $1.50
160	Grok 4.1 Fast	xAI	1398	1389–1407	4.5K	—
161	NVIDIA-Nemotron-3-Super-120B-A12B	NVIDIA	1398	1376–1420	656	—
163	Qwen3-30B-A3B-Instruct	Alibaba	1396	1380–1413	1.2K	$0.09 / $0.30
164	GPT-5.3 Chat	OpenAI	1396	1385–1408	3K	—
165	GPT-5.4 nano	OpenAI	1396	1388–1404	6.4K	$0.20 / $1.25
166	Hunyuan T1	Tencent	1395	1357–1433	216	—
167	Grok 3 Mini	xAI	1395	1376–1413	911	—
168	GPT-4.5 Preview	OpenAI	1394	1371–1418	608	—
169	DeepSeek-R1	DeepSeek	1394	1374–1413	887	$0.50 / $2.15
170	Muse Glimmer	Meta	1391	1362–1419	458	—
171	Granite 4.2 8B	IBM	1386	1353–1418	317	$0.06 / $0.25
172	Claude Opus 4	Anthropic	1386	1372–1400	1.8K	—
174	Grok 4.3	xAI	1384	1377–1392	7.5K	$1.25 / $2.50
175	GPT-5 mini	OpenAI	1379	1362–1396	1.2K	$0.25 / $2
176	MiniMax-M2.5	MiniMax	1379	1369–1389	3.8K	$0.30 / $1.20
177	Qwen3-Next-80B-A3B-Thinking	Alibaba	1376	1353–1398	661	$0.15 / $1.20
178	Gemini 2.5 Flash-Lite Preview	Google	1374	1363–1385	2.8K	$0.10 / $0.40
179	Claude Sonnet 4	Anthropic	1372	1358–1387	1.7K	—
180	GLM-4.6V	Z.ai	1371	1329–1413	184	$0.30 / $0.90
181	GLM-4.5-Air	Z.ai	1370	1355–1386	1.5K	$0.13 / $0.85
183	Qwen3-235B-A22B	Alibaba	1369	1356–1383	1.9K	$0.09 / $0.55
184	Grok 3 Mini Beta	xAI	1366	1349–1383	1.1K	—
186	Kimi K2 Preview	Moonshot AI	1365	1341–1389	575	$0.60 / $2.50
187	o3-mini	OpenAI	1364	1344–1385	847	$1.10 / $4.40
188	GPT-4.1	OpenAI	1364	1353–1376	2.6K	$2 / $8
189	Qwen3-32B	Alibaba	1362	1326–1399	236	$0.08 / $0.28
190	o1	OpenAI	1362	1345–1378	1.3K	$15 / $60
191	Trinity Large Thinking	Arcee	1359	1347–1371	2.9K	$0.25 / $0.80
192	Amazon Nova 2 Lite	Amazon	1359	1338–1379	788	—
193	Mercury 2	Inception	1358	1323–1393	253	$0.25 / $0.75
194	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	NVIDIA	1357	1345–1370	2.4K	—
195	GLM-4.7-Flash	Z.ai	1357	1338–1376	888	$0.06 / $0.40
196	gpt-oss-120b	OpenAI	1356	1341–1372	1.4K	$0.15 / $0.60
197	NVIDIA-Nemotron-3-Nano-30B-A3B	NVIDIA	1356	1338–1374	1K	—
198	LLing-flash-2.0	Ant Group	1354	1324–1383	355	—
199	GLM-4.5V	Z.ai	1353	1312–1394	190	$0.60 / $1.80
200	Trinity Large Preview	Arcee	1351	1340–1363	2.9K	—
201	DeepSeek-V3	DeepSeek	1351	1339–1363	2.4K	$0.29 / $1.14
204	o4-mini	OpenAI	1343	1331–1355	2.3K	$1.10 / $4.40
205	RRing-flash-2.0	Ant Group	1343	1312–1374	359	—
206	Mistral Medium 3	Mistral AI	1342	1329–1355	1.8K	$0.40 / $2
207	Gemini 2.0 Flash	Google	1339	1327–1352	2.2K	—
208	Hunyuan TurboS	Tencent	1339	1315–1362	587	—
209	Qwen3-Coder-480B-A35B-Instruct	Alibaba	1338	1322–1354	1.4K	—
210	GPT-4.1 mini	OpenAI	1338	1325–1351	2K	$0.40 / $1.60
213	MiniMax-M2	MiniMax	1338	1305–1370	301	$0.26 / $1.02
214	Qwen2.5-Max	Alibaba	1337	1323–1351	1.7K	—
216	Step-3	StepFun	1333	1298–1368	265	—
217	Llama 3.3 Nemotron Super 49B v1.5	NVIDIA	1330	1289–1371	180	—
219	Qwen-Plus	Alibaba	1328	1298–1357	358	$0.26 / $0.78
220	QwQ-32B	Alibaba	1323	1307–1340	1.2K	—
221	IINTELLECT-3	—	1322	1290–1353	355	—
222	GPT-5 nano	OpenAI	1321	1289–1353	338	$0.05 / $0.40
223	Claude 3.7 Sonnet	Anthropic	1321	1307–1335	1.9K	—
224	MiniMax-M1	MiniMax	1317	1303–1332	1.6K	$0.55 / $2.20
225	o1-mini	OpenAI	1316	1304–1328	3.2K	—
226	Qwen3-30B-A3B	Alibaba	1315	1298–1331	1.3K	$0.12 / $0.50
227	Granite 4.2 3B	IBM	1314	1279–1350	317	—
228	Granite 4.1 8B	IBM	1309	1278–1340	411	—
229	Olmo 3.1 32B Instruct	Ai2	1309	1287–1330	760	—
230	Step-1o Turbo	StepFun	1308	1281–1334	484	—
232	Gemini 2.0 Flash-Lite Preview	Google	1305	1288–1321	1.2K	—
233	Gemma 3 27B IT	Google	1304	1291–1316	2.3K	$0.08 / $0.35
235	Command A	Cohere	1296	1285–1307	2.9K	$0.30 / $1.50
236	Olmo 3.1 32B Think	Ai2	1295	1270–1320	556	—
237	Mistral Small 3.2	Mistral AI	1291	1272–1311	856	—
238	Qwen2.5-Plus	Alibaba	1289	1268–1310	664	—
239	Yi Lightning	01.AI	1286	1271–1300	1.5K	—
240	GLM-4-Plus	Z.ai	1279	1250–1309	354	—
241	Step-2 16K Exp	StepFun	1279	1248–1309	310	—
242	Gemini 1.5 Pro	Google	1279	1268–1290	3.3K	—
243	Hunyuan Large	Tencent	1276	1240–1311	228	—
244	Olmo 3 32B Think	Ai2	1274	1238–1309	313	—
245	GPT-4.1 nano	OpenAI	1272	1241–1302	328	$0.10 / $0.40
246	AAthene V2 Chat	—	1268	1253–1283	1.5K	—
247	DeepSeek-V2.5	DeepSeek	1266	1240–1292	441	—
248	Claude 3.5 Sonnet	Anthropic	1265	1255–1274	5K	—
249	Llama 4 Maverick 17B 128E Instruct	Meta	1259	1246–1273	2K	—
250	gpt-oss-20b	OpenAI	1258	1231–1285	506	$0.018 / $0.09
251	Mistral Small 3.1 24B Instruct	Mistral AI	1257	1242–1272	1.7K	$0.35 / $0.56
252	Grok 2	xAI	1254	1243–1265	3.5K	—
254	Hunyuan Large Vision	Tencent	1252	1218–1286	293	—
255	Granite-4.0-H-Small	IBM	1251	1217–1285	316	—
256	GPT-4o	OpenAI	1250	1240–1260	5.9K	$2.50 / $10
257	Qwen-Max	Alibaba	1248	1230–1266	1K	—
258	Gemma 3 12B IT	Google	1248	1207–1288	186	$0.05 / $0.15
259	Hunyuan Standard	Tencent	1248	1209–1286	207	—
261	Gemma 3n E4B IT	Google	1246	1228–1264	1.1K	—
262	Qwen2.5-72B-Instruct	Alibaba	1245	1233–1257	2.4K	$0.36 / $0.40
264	Llama 3.1 405B Instruct	Meta	1243	1232–1254	3.1K	—
265	Llama 3.1 Nemotron 70B Instruct	NVIDIA	1242	1216–1269	453	—
268	Grok 2 mini	xAI	1238	1226–1250	2.8K	—
269	Llama 4 Scout 17B 16E Instruct	Meta	1235	1220–1251	1.5K	—
270	GPT-4o mini	OpenAI	1235	1224–1245	3.6K	$0.15 / $0.60
271	Gemini 1.5 Flash	Google	1233	1220–1246	2.1K	—
272	Mistral Large 2	Mistral AI	1232	1220–1245	2.5K	—
274	AAthene 70B	—	1228	1209–1247	867	—
275	Llama 3.3 70B Instruct	Meta	1225	1214–1237	2.9K	$0.10 / $0.32
276	Magistral Medium	Mistral AI	1223	1197–1250	565	—
277	GPT-4 Turbo	OpenAI	1223	1212–1234	5.2K	$10 / $30
278	Gemma 3 4B IT	Google	1223	1182–1264	208	$0.04 / $0.05
279	Claude 3 Opus	Anthropic	1223	1213–1232	10.4K	—
280	Qwen2.5-Coder-32B-Instruct	Alibaba	1221	1188–1253	267	$0.66 / $1
281	Jamba 1.5 Large	AI21 Labs	1218	1189–1247	331	—
282	Gemini Advanced	Google	1215	1201–1229	2.4K	—
283	Reka Core	Reka	1214	1189–1238	458	—
285	Amazon Nova Pro 1.0	Amazon	1211	1195–1227	1.4K	—
286	Llama 3.1 70B Instruct	Meta	1209	1197–1220	2.9K	$0.40 / $0.40
287	Mistral Large	Mistral AI	1208	1193–1223	1.5K	$0.50 / $1.50
288	Claude 3.5 Haiku	Anthropic	1208	1197–1218	3.5K	—
290	Phi-4	Microsoft	1203	1186–1220	1.1K	$0.07 / $0.14
291	Mistral Small 24B Instruct	Mistral AI	1202	1181–1222	754	$0.05 / $0.08
292	Amazon Nova Lite 1.0	Amazon	1201	1185–1218	1.1K	—
294	Gemini 1.5 Flash-8B	Google	1185	1172–1198	2.1K	—
295	Amazon Nova Micro 1.0	Amazon	1184	1166–1201	1.1K	—
296	Aya Expanse 32B	Cohere	1182	1168–1196	1.8K	—
297	Reka Flash	Reka	1182	1159–1205	493	—
298	DeepSeek-Coder-V2	DeepSeek	1181	1160–1203	769	—
299	GLM-4	Z.ai	1179	1154–1204	514	—
300	Command R+	Cohere	1174	1149–1198	524	$0.15 / $0.60
301	Claude 3 Sonnet	Anthropic	1173	1161–1184	5.6K	—
302	Gemma 2 27B IT	Google	1172	1161–1182	4K	$0.65 / $0.65
303	Nemotron-4 340B Instruct	NVIDIA	1171	1153–1190	1K	—
304	Qwen2-72B-Instruct	Alibaba	1171	1157–1186	1.8K	—
305	Ministral 8B	Mistral AI	1170	1140–1200	332	$0.15 / $0.15
306	Llama 3.1 Nemotron 51B Instruct	NVIDIA	1167	1134–1200	265	—
307	Gemma 2 9B IT SimPO	Google	1155	1125–1184	369	—
309	Aya Expanse 8B	Cohere	1153	1129–1176	600	—
310	IInternLM2.5 20B Chat	—	1151	1129–1173	604	—
311	Llama 3 70B Instruct	Meta	1149	1138–1160	8K	—
312	GPT-4	OpenAI	1149	1134–1164	2.2K	$30 / $60
313	Claude 3 Haiku	Anthropic	1148	1137–1159	6.3K	—
314	Gemma 2 9B IT	Google	1147	1135–1159	2.8K	—
315	Qwen1.5-110B-Chat	Alibaba	1144	1128–1161	1.4K	—
316	Yi 1.5 34B Chat	01.AI	1144	1126–1162	1K	—
317	Llama 3.1 8B Instruct	Meta	1144	1132–1156	2.6K	$0.05 / $0.08
318	Granite 3.1 8B Instruct	IBM	1142	1107–1177	237	—
320	Qwen1.5-72B-Chat	Alibaba	1136	1121–1151	1.8K	—
321	Jamba 1.5 Mini	AI21 Labs	1136	1105–1166	332	—
323	Granite 3.1 2B Instruct	IBM	1131	1096–1166	225	—
325	Qwen1.5-32B-Chat	Alibaba	1126	1108–1144	1.2K	—
326	Mistral Medium	Mistral AI	1125	1108–1142	1.4K	—
328	Reka Flash 21B	Reka	1116	1095–1138	830	—
329	Llama 3 8B Instruct	Meta	1113	1102–1125	5.4K	—
330	Mixtral 8x22B Instruct v0.1	Mistral AI	1113	1100–1127	2.6K	—
331	Phi-3 Medium 4K Instruct	Microsoft	1108	1090–1126	1.1K	—
334	Gemma 2 2B IT	Google	1096	1084–1109	2.5K	—
335	Qwen1.5-14B-Chat	Alibaba	1094	1074–1114	944	—
336	Llama 3.2 3B Instruct	Meta	1090	1066–1114	499	$0.051 / $0.34
337	Mixtral 8x7B Instruct v0.1	Mistral AI	1088	1075–1101	3.2K	—
338	Granite 3.0 8B Instruct	IBM	1087	1057–1118	345	—
339	SStarling LM 7B Beta	—	1084	1064–1104	952	—
340	DDBRX Instruct Preview	—	1076	1060–1092	1.7K	—
341	GPT-3.5 Turbo	OpenAI	1070	1042–1098	437	$1 / $2
342	Phi-3 Small 8K Instruct	Microsoft	1067	1048–1086	895	—
344	Granite 3.0 2B Instruct	IBM	1064	1036–1093	407	—
345	ZZephyr ORPO 141B A35B v0.1	—	1062	1022–1102	219	—
346	Yi 34B Chat	01.AI	1061	1037–1086	559	—
347	Gemini Pro	Google	1059	1036–1082	694	$2 / $10
348	Qwen1.5-7B-Chat	Alibaba	1055	1019–1091	231	—
349	OOpenChat 3.5	—	1053	1030–1075	611	—
350	Phi-3 Mini 4K Instruct	Microsoft	1051	1025–1077	486	—
353	Gemma 1.1 7B IT	Google	1039	1022–1057	1.2K	—
354	Llama 2 70B Chat	Meta	1039	1022–1057	1.4K	—
355	Llama 2 7B Chat	Meta	1036	1008–1064	411	—
356	Mistral 7B Instruct v0.2	Mistral AI	1036	1015–1057	798	—
357	SStarling LM 7B Alpha	—	1033	1003–1064	318	—
358	Llama 2 13B Chat	Meta	1030	1005–1055	539	—
359	VVicuna 33B	—	1029	1003–1056	484	—
360	Snowflake Arctic Instruct	Snowflake	1028	1011–1046	1.7K	—
361	Llama 3.2 1B Instruct	Meta	1007	980–1034	487	$0.027 / $0.20
362	ZZephyr 7B Beta	—	1006	969–1043	201	—
363	Gemma 7B IT	Google	1002	971–1032	340	—
364	VVicuna 13B	—	994	963–1025	321	—
365	Phi-3 Mini 128K Instruct	Microsoft	984	964–1004	1.1K	—
366	Qwen1.5-4B-Chat	Alibaba	980	949–1011	356	—
367	Gemma 1.1 2B IT	Google	970	945–996	578	—
368	Mistral 7B Instruct	Mistral AI	954	915–993	183	—

Show all 305 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 Text
• LMArena Coding
• LMArena Math
• LMArena Creative writing
• LMArena Instruction following
• LMArena Hard prompts
• LMArena Multi-turn
• LMArena Long queries