LMArena Instruction following leaderboard

LMArena’s text votes on prompts with specific instructions to follow. Claude Opus 5.5 leads with a rating of 1539.

Models: 351
Leader: Claude Opus 5.5
Source: LMArena
As of: Oct 22, 2026

LMArena Instruction following, rating against blended price per million tokens

Open weightsProprietaryBest for the price

Full leaderboard

Rank	Model	Lab	Rating	95% interval	Votes	Price in / out
1	Claude Opus 5.5	Anthropic	1539	1528–1550	3.6K	$4 / $20
2	Gemini 4 Argon	Google	1528	1517–1538	3.6K	$2 / $10
3	Claude Opus 4.6	Anthropic	1521	1516–1526	26.9K	$5 / $25
4	Claude Fable 5.1	Anthropic	1519	1510–1528	4.9K	$10 / $50
5	Claude Opus 5	Anthropic	1518	1512–1525	12K	$5 / $25
8	Claude Fable 5	Anthropic	1502	1496–1507	15.6K	$10 / $50
9	Claude Opus 4.7	Anthropic	1498	1492–1503	22.7K	$5 / $25
10	Muse Wonder	Meta	1493	1479–1506	2.1K	$4 / $20
11	Gemini 3.8 Flash	Google	1492	1485–1498	15.8K	$0.82 / $4.13
12	MiMo-V2.6-Pro	Xiaomi	1491	1475–1506	1.4K	$0.43 / $0.87
13	Claude Sonnet 5.5	Anthropic	1491	1479–1502	3K	$2 / $10
15	Gemini 3.7 Flash	Google	1486	1479–1493	11K	$0.75 / $3.75
16	Kimi K3	Moonshot AI	1485	1478–1491	11.8K	$0.24 / $11
17	GPT-5.6 Sol	OpenAI	1483	1477–1489	14.9K	$4 / $20
18	Qwen3.8-Max	Alibaba	1481	1474–1487	10.8K	$2 / $6
19	GLM-5.3	Z.ai	1480	1473–1488	8.4K	$0.079 / $1.40
20	GLM-5.3-Flash	Z.ai	1479	1473–1486	13.3K	$0.15 / $0.50
21	Muse Spark 1.3	Meta	1479	1471–1487	7.3K	$1.25 / $4.25
22	GPT-5.5	OpenAI	1479	1473–1484	24K	$5 / $30
23	Claude Opus 4.5	Anthropic	1478	1471–1485	9.9K	$5 / $25
24	Claude Opus 4.8	Anthropic	1477	1471–1482	22.7K	$5 / $25
25	Claude Sonnet 4.6	Anthropic	1476	1471–1481	23.7K	$3 / $15
26	MiMo-V2.5-Pro	Xiaomi	1475	1470–1480	26K	$0.30 / $0.61
28	DeepSeek-V4.1-Flash-20260910	DeepSeek	1474	1465–1483	4.8K	$0.15 / $0.60
30	GPT-5.4	OpenAI	1469	1464–1475	21.9K	$2.50 / $15
31	Gemini 3.6 Flash	Google	1467	1461–1473	13.1K	$0.75 / $3.75
32	GPT-6.1 Sol	OpenAI	1467	1455–1479	2.5K	$2 / $10
33	Gemini 3.5 Flash	Google	1467	1461–1472	17.4K	$1.50 / $9
34	Qwen3.5-Max-Preview	Alibaba	1467	1459–1474	7.4K	—
35	Gemini 3.1 Pro Preview	Google	1466	1462–1470	44.8K	$2 / $12
36	GLM-5.2	Z.ai	1466	1460–1471	18K	$0.034 / $7
39	Muse Spark 1.2	Meta	1463	1453–1473	3.7K	$1.25 / $4.25
40	Qwen3.7-Max-Preview	Alibaba	1460	1444–1477	1.4K	$1.48 / $4.42
41	ERNIE 5.1	Baidu	1460	1454–1467	12.7K	—
42	Claude Sonnet 4.5	Anthropic	1459	1454–1464	24.4K	$3 / $15
43	Gemini 3 Pro	Google	1458	1452–1464	11.7K	—
45	Muse Spark 1.1	Meta	1456	1451–1462	16.5K	$1.25 / $4.25
46	GPT-5.6 Terra	OpenAI	1455	1450–1461	16.6K	$2 / $12
47	GPT-6 Astra	OpenAI	1455	1446–1465	4.4K	$10 / $50
49	GLM-5.1	Z.ai	1452	1448–1457	22.9K	$1.40 / $4.40
50	Claude Sonnet 5	Anthropic	1452	1447–1458	18.2K	$2 / $10
51	Kimi K2.6	Moonshot AI	1451	1444–1457	13.2K	$0.65 / $3.41
52	MiMo-V2.6-Flash	Xiaomi	1449	1440–1458	4.6K	$0.14 / $0.28
53	DeepSeek-V4-Pro	DeepSeek	1448	1438–1458	3.5K	$0.66 / $1.98
54	Grok 4.5	xAI	1445	1439–1451	14.5K	$2 / $6
56	MiMo-V2-Pro	Xiaomi	1445	1438–1452	8.4K	—
57	GPT-5.1	OpenAI	1443	1436–1449	11.2K	$1.25 / $10
58	Muse Spark	Meta	1443	1434–1452	4.7K	—
59	Step 5 Preview	StepFun	1441	1430–1451	3.4K	$1 / $2.70
60	Qwen3.7-Plus	Alibaba	1440	1434–1446	15K	$0.32 / $1.28
61	Qwen3.6-Max-Preview	Alibaba	1440	1426–1453	1.9K	—
62	GPT-5.6 Luna	OpenAI	1438	1432–1444	14.7K	$0.20 / $1.20
63	Gemini 3 Flash	Google	1437	1430–1444	8.5K	$0.50 / $3
64	Gemini 2.5 Pro	Google	1437	1433–1440	35.2K	$1.25 / $10
65	Qwen3.8-27B	Alibaba	1436	1429–1443	9.3K	$0.20 / $2.50
67	Claude Opus 4.1	Anthropic	1435	1430–1441	13.2K	$15 / $75
68	MiMo-V2.5	Xiaomi	1435	1429–1441	16.1K	$0.12 / $0.24
69	Gemma 4 31B	Google	1434	1420–1447	1.8K	$0.20 / $0.40
71	MiniMax-M3	MiniMax	1432	1427–1437	23.3K	$0.30 / $1.20
72	Grok 4.6	xAI	1432	1426–1439	11.4K	$2 / $6
73	Beam 1.0 501B A23B	Reflection AI	1431	1416–1446	1.6K	$0.25 / $1
74	Kimi K2.5	Moonshot AI	1431	1426–1436	24.2K	$0.50 / $2.50
76	MiMo-V2-Omni	Xiaomi	1429	1421–1437	7.1K	—
77	GLM-5	Z.ai	1428	1421–1434	9.6K	$1 / $3.20
78	amazon-nova-experimental-chat	Amazon	1427	1409–1445	995	—
79	Hy3	Tencent	1427	1418–1436	4.8K	$0.083 / $0.33
80	Inkling	Thinky	1425	1419–1431	15.7K	$1 / $4.05
81	Qwen3.6-Plus	Alibaba	1424	1419–1430	16.5K	$0.33 / $1.95
82	GLM-5V-Turbo	Z.ai	1424	1414–1434	3.7K	$1.20 / $4
83	Mistral Large 4	Mistral AI	1424	1414–1434	3.6K	$1.36 / $4.18
84	Qwen3.5-397B-A17B	Alibaba	1424	1419–1428	33K	$0.50 / $3.60
85	DeepSeek-V4-Flash	DeepSeek	1421	1415–1427	18K	$0.042 / $0.18
86	Grok 4.20 Beta	xAI	1421	1415–1426	22.6K	—
87	Gemma 4 26B A4B	Google	1420	1407–1434	1.7K	$0.068 / $0.23
88	Grok 4.20 Multi-Agent Beta	xAI	1420	1415–1426	22K	—
89	Qwen3-Max-Preview	Alibaba	1420	1412–1427	7.3K	—
90	Gemini 3.5 Flash-Lite	Google	1419	1413–1426	12.9K	$0.30 / $2.50
92	NVIDIA-Nemotron-3-Ultra-550B-A55B	NVIDIA	1418	1408–1428	3.9K	—
94	GPT-5.2 Chat	OpenAI	1417	1411–1423	11.8K	$1.75 / $14
95	Claude Haiku 5.5	Anthropic	1416	1403–1429	2.1K	$0.10 / $0.50
96	Grok 4.20 Beta 1	xAI	1415	1408–1422	8.8K	—
97	Mistral Medium 3.5	Mistral AI	1415	1405–1425	3.8K	$1.50 / $7.50
98	Claude Haiku 4.5	Anthropic	1414	1411–1418	48.9K	$1 / $5
100	Dola Seed 2.0 Pro	ByteDance	1414	1409–1419	26.3K	—
101	ERNIE 5.0	Baidu	1413	1407–1419	11.1K	—
102	DeepSeek-V3.2-Exp	DeepSeek	1413	1407–1419	13.6K	$0.28 / $0.42
103	GLM-4.7	Z.ai	1412	1402–1422	3.3K	$0.54 / $1.98
104	GPT-6 Sol	OpenAI	1411	1402–1420	4.9K	$2 / $10
105	LongCat-Flash-Chat Exp	Meituan	1411	1404–1418	9.6K	—
106	GLM-4.6	Z.ai	1410	1404–1417	10.3K	$0.55 / $2.20
107	GPT-5.2	OpenAI	1409	1404–1415	15.3K	$1.75 / $14
108	Grok 3 Preview	xAI	1409	1402–1415	9.6K	—
110	Grok 4.7	xAI	1408	1399–1417	4.9K	$2 / $6
111	Qwen3-235B-A22B-Instruct	Alibaba	1408	1404–1412	27.8K	$0.09 / $0.55
112	GPT-6 Luna	OpenAI	1407	1401–1413	24.6K	$0.10 / $0.50
113	GPT-5.5 Instant	OpenAI	1407	1400–1414	9.7K	—
114	Qwen3-VL-235B-A22B-Instruct	Alibaba	1407	1395–1418	2.9K	$0.21 / $1.90
115	Claude Opus 4	Anthropic	1406	1399–1413	9.2K	—
116	MiniMax-M2.7	MiniMax	1405	1401–1410	29.4K	$0.30 / $1.20
117	Gemini 2.5 Flash	Google	1405	1401–1409	34.8K	$0.30 / $2.50
118	GPT-5.4 mini	OpenAI	1405	1400–1410	21.7K	$0.75 / $4.50
119	GLM-4.5	Z.ai	1404	1397–1412	6.2K	$0.60 / $2.20
120	DeepSeek-V3.1-Terminus	DeepSeek	1404	1384–1424	859	$0.27 / $1
121	Mistral Large 3	Mistral AI	1404	1400–1408	28.2K	$0.50 / $1.50
122	GPT-4.5 Preview	OpenAI	1404	1396–1412	5.5K	—
123	Kimi K2 Thinking Turbo	Moonshot AI	1403	1398–1408	18.7K	—
124	ChatGPT-4o Latest	OpenAI	1403	1399–1408	23K	—
128	DeepSeek-V3.1	DeepSeek	1401	1389–1412	2.8K	$0.25 / $0.95
130	MiniMax-M2.1 Preview	MiniMax	1400	1391–1409	4.7K	$0.30 / $1.20
131	Grok 4.1	xAI	1400	1395–1405	19.5K	—
132	Qwen3.5-122B-A10B	Alibaba	1400	1393–1406	9.6K	$0.40 / $3.20
133	Inkling-Small	Thinky	1399	1393–1405	12.9K	$0.45 / $1.20
136	Mistral Medium 3.1	Mistral AI	1398	1394–1402	27.6K	$0.40 / $2
137	NVIDIA-Nemotron-3.5-Super-VL-120B-A12B	NVIDIA	1398	1382–1413	1.4K	—
138	Hunyuan Vision 1.5 Thinking	Tencent	1397	1375–1420	625	—
141	Qwen3.5-27B	Alibaba	1393	1386–1400	9.2K	$0.27 / $2.16
142	MiMo-V2-Flash	Xiaomi	1393	1387–1398	14.8K	—
144	Qwen3-Next-80B-A3B-Instruct	Alibaba	1389	1381–1396	6.4K	$0.09 / $1.10
145	GPT-5	OpenAI	1388	1381–1395	8.4K	$1.25 / $10
147	Grok 4 Fast	xAI	1387	1372–1401	1.7K	—
148	Grok 4	xAI	1387	1381–1393	10.8K	—
151	Qwen3-235B-A22B-Thinking	Alibaba	1386	1374–1398	2.1K	$0.45 / $3.50
152	Step-3.5-Flash	StepFun	1385	1380–1390	19.3K	$0.10 / $0.30
155	DeepSeek-R1	DeepSeek	1381	1372–1391	4K	$0.50 / $2.15
156	GPT-5 Chat	OpenAI	1381	1374–1388	8.2K	—
159	Qwen3.5-35B-A3B	Alibaba	1379	1373–1386	9.9K	$0.14 / $1
160	GPT-5.3 Chat	OpenAI	1378	1372–1385	11.2K	—
161	Gemini 3.1 Flash-Lite Preview	Google	1377	1372–1383	21.5K	$0.25 / $1.50
162	Grok 4.1 Fast	xAI	1376	1371–1381	17.3K	—
163	Muse Glimmer	Meta	1376	1360–1392	1.4K	—
164	Claude Sonnet 4	Anthropic	1376	1369–1383	8.5K	—
165	Hunyuan T1	Tencent	1375	1358–1393	1.1K	—
166	Qwen3-VL-235B-A22B-Thinking	Alibaba	1375	1363–1387	2.2K	—
167	Qwen3.5-Flash	Alibaba	1375	1369–1380	20.3K	$0.065 / $0.26
168	Solar Pro 4	Upstage	1374	1367–1382	8.8K	$0.15 / $0.60
171	o3	OpenAI	1368	1362–1373	15.5K	$2 / $8
172	o1	OpenAI	1367	1361–1374	10.2K	$15 / $60
173	GPT-4.1	OpenAI	1367	1361–1373	13.3K	$2 / $8
174	Gemini 2.5 Flash-Lite Preview	Google	1367	1360–1374	8.1K	$0.10 / $0.40
175	Grok 4.3	xAI	1365	1360–1371	25.1K	$1.25 / $2.50
177	Qwen3-30B-A3B-Instruct	Alibaba	1363	1355–1371	6K	$0.09 / $0.30
178	GPT-5.4 nano	OpenAI	1362	1357–1368	21.5K	$0.20 / $1.25
179	Qwen3-235B-A22B	Alibaba	1362	1355–1369	9.2K	$0.09 / $0.55
181	GPT-5 mini	OpenAI	1357	1349–1364	7K	$0.25 / $2
182	Grok 3 Mini	xAI	1357	1348–1366	4.2K	—
183	Qwen3-Coder-480B-A35B-Instruct	Alibaba	1356	1348–1363	6.2K	—
185	GLM-4.5-Air	Z.ai	1354	1347–1361	8.2K	$0.13 / $0.85
186	MiniMax-M2.5	MiniMax	1353	1347–1359	13.8K	$0.30 / $1.20
188	Claude 3.7 Sonnet	Anthropic	1352	1345–1358	10.1K	—
189	GLM-4.6V	Z.ai	1351	1329–1372	753	$0.30 / $0.90
190	Kimi K2 Preview	Moonshot AI	1348	1337–1359	2.9K	$0.60 / $2.50
191	NVIDIA-Nemotron-3-Super-120B-A12B	NVIDIA	1347	1335–1360	2.2K	—
192	Granite 4.2 30B	IBM	1347	1329–1365	1.2K	—
193	Grok 3 Mini Beta	xAI	1346	1338–1354	5.4K	—
194	DeepSeek-V3	DeepSeek	1345	1339–1350	12.4K	$0.29 / $1.14
195	Hunyuan TurboS	Tencent	1344	1332–1356	2.4K	—
196	Qwen3-Next-80B-A3B-Thinking	Alibaba	1343	1333–1353	3.5K	$0.15 / $1.20
198	Mistral Medium 3	Mistral AI	1338	1331–1345	7.9K	$0.40 / $2
199	o3-mini	OpenAI	1337	1330–1345	6.7K	$1.10 / $4.40
200	Gemini 2.0 Flash	Google	1336	1330–1341	13.6K	—
201	Amazon Nova 2 Lite	Amazon	1335	1325–1345	3.4K	—
202	Qwen2.5-Max	Alibaba	1335	1329–1341	11K	—
203	Trinity Large Preview	Arcee	1334	1327–1341	9.7K	—
205	GPT-4.1 mini	OpenAI	1333	1326–1339	10K	$0.40 / $1.60
206	Step-3	StepFun	1332	1318–1347	1.6K	—
207	MiniMax-M2	MiniMax	1329	1316–1342	2K	$0.26 / $1.02
208	Mercury 2	Inception	1327	1308–1346	885	$0.25 / $0.75
209	GLM-4.7-Flash	Z.ai	1327	1316–1337	3.3K	$0.06 / $0.40
210	Trinity Large Thinking	Arcee	1326	1319–1333	10.3K	$0.25 / $0.80
213	Gemma 3 27B IT	Google	1321	1315–1326	12.5K	$0.08 / $0.35
214	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	NVIDIA	1321	1313–1328	7.6K	—
215	o4-mini	OpenAI	1320	1314–1326	11.9K	$1.10 / $4.40
216	Ling-flash-2.0	Ant Group	1319	1305–1332	1.8K	—
217	gpt-oss-120b	OpenAI	1318	1311–1325	7.9K	$0.15 / $0.60
219	INTELLECT-3	—	1316	1300–1331	1.5K	—
223	Ring-flash-2.0	Ant Group	1314	1300–1327	1.9K	—
224	MiniMax-M1	MiniMax	1312	1305–1319	8.6K	$0.55 / $2.20
225	GLM-4.5V	Z.ai	1311	1295–1326	1.3K	$0.60 / $1.80
226	Step-1o Turbo	StepFun	1310	1297–1323	2.1K	—
227	Mistral Small 3.2	Mistral AI	1309	1300–1318	4.4K	—
228	Command A	Cohere	1309	1303–1314	15.6K	$0.30 / $1.50
229	Llama 3.1 Nemotron Ultra 253B v1	NVIDIA	1308	1287–1329	660	—
230	GPT-5 nano	OpenAI	1306	1293–1319	2K	$0.05 / $0.40
231	Qwen3-32B	Alibaba	1305	1286–1323	858	$0.08 / $0.28
232	Gemini 2.0 Flash-Lite Preview	Google	1305	1298–1311	9.2K	—
233	o1-mini	OpenAI	1304	1299–1309	21.5K	—
234	NVIDIA-Nemotron-3-Nano-30B-A3B	NVIDIA	1304	1295–1313	4.4K	—
235	Qwen-Plus	Alibaba	1303	1291–1315	2.2K	$0.26 / $0.78
236	Granite 4.2 8B	IBM	1301	1282–1320	1.1K	$0.06 / $0.25
237	Olmo 3.1 32B Instruct	Ai2	1299	1289–1310	3.2K	—
238	Gemma 3 12B IT	Google	1299	1283–1315	1.1K	$0.05 / $0.15
239	Llama 3.3 Nemotron Super 49B v1.5	NVIDIA	1299	1279–1319	807	—
240	QwQ-32B	Alibaba	1297	1290–1304	7.2K	—
241	Claude 3.5 Sonnet	Anthropic	1297	1293–1301	31.2K	—
242	Gemini 1.5 Pro	Google	1297	1292–1302	22.8K	—
243	Llama 3.3 Nemotron Super 49B v1	NVIDIA	1293	1274–1313	803	—
244	GLM-4-Plus	Z.ai	1292	1280–1305	2.2K	—
245	Step-2 16K Exp	StepFun	1287	1274–1299	2K	—
246	Qwen3-30B-A3B	Alibaba	1283	1276–1291	6.1K	$0.12 / $0.50
247	DeepSeek-V2.5	DeepSeek	1280	1268–1291	3K	—
248	Hunyuan Turbo	Tencent	1278	1260–1296	842	—
249	Yi Lightning	01.AI	1278	1271–1285	10.9K	—
250	GPT-4o	OpenAI	1278	1273–1283	43.8K	$2.50 / $10
251	Hunyuan Large	Tencent	1277	1262–1293	1.3K	—
252	Qwen2.5-Plus	Alibaba	1275	1266–1284	4.2K	—
253	Olmo 3 32B Think	Ai2	1274	1259–1290	1.5K	—
254	Granite 4.2 3B	IBM	1274	1254–1293	1.1K	—
255	Athene V2 Chat	—	1271	1264–1277	10.2K	—
256	Molmo 2 8B	Ai2	1270	1233–1307	220	—
257	Grok 2	xAI	1270	1265–1275	25.7K	—
259	Granite 4.1 8B	IBM	1268	1251–1285	1.4K	—
260	Llama 4 Maverick 17B 128E Instruct	Meta	1267	1261–1273	10.5K	—
262	GPT-4.1 nano	OpenAI	1266	1254–1279	2K	$0.10 / $0.40
264	Mistral Small 3.1 24B Instruct	Mistral AI	1263	1256–1270	8K	$0.35 / $0.56
265	Qwen-Max	Alibaba	1262	1254–1270	6.9K	—
267	Llama 3.1 405B Instruct	Meta	1259	1253–1264	23.6K	—
268	GPT-4o mini	OpenAI	1258	1254–1263	26.7K	$0.15 / $0.60
269	Gemini 1.5 Flash	Google	1257	1252–1263	14.6K	—
270	Gemma 3n E4B IT	Google	1255	1247–1264	5K	—
271	Qwen2.5-72B-Instruct	Alibaba	1254	1248–1260	16.4K	$0.36 / $0.40
273	Magistral Medium	Mistral AI	1254	1243–1264	3.1K	—
274	Gemini Advanced	Google	1253	1247–1260	18.5K	—
275	Llama 3.1 Nemotron 70B Instruct	NVIDIA	1252	1241–1263	3K	—
276	Hunyuan Large Vision	Tencent	1250	1233–1267	1.2K	—
277	GPT-4 Turbo	OpenAI	1249	1244–1255	36.3K	$10 / $30
279	Mistral Large	Mistral AI	1249	1243–1255	11K	$0.50 / $1.50
280	Claude 3 Opus	Anthropic	1248	1244–1253	72K	—
281	Llama 4 Scout 17B 16E Instruct	Meta	1248	1240–1255	7.5K	—
282	Mistral Large 2	Mistral AI	1248	1242–1253	18.3K	—
283	Olmo 3.1 32B Think	Ai2	1246	1233–1259	2.2K	—
284	Hunyuan Standard	Tencent	1245	1230–1260	1.3K	—
285	Grok 2 mini	xAI	1245	1239–1250	21.1K	—
286	Llama 3.3 70B Instruct	Meta	1242	1237–1247	18.8K	$0.10 / $0.32
287	Claude 3.5 Haiku	Anthropic	1241	1236–1245	21.9K	—
289	Mercury	Inception	1240	1215–1265	589	—
290	Gemma 3 4B IT	Google	1239	1223–1255	1.2K	$0.04 / $0.05
291	gpt-oss-20b	OpenAI	1236	1224–1248	2.5K	$0.018 / $0.09
292	Amazon Nova Pro 1.0	Amazon	1235	1229–1242	9.5K	—
294	Llama 3.1 Tulu 3 70B	Ai2	1233	1217–1248	1.2K	—
295	Llama 3.1 70B Instruct	Meta	1231	1226–1236	21.9K	$0.40 / $0.40
296	Athene 70B	—	1227	1219–1234	7.5K	—
297	Qwen2.5-Coder-32B-Instruct	Alibaba	1223	1211–1235	2.2K	$0.66 / $1
298	Granite-4.0-H-Small	IBM	1223	1207–1238	1.6K	—
299	Mistral Small 24B Instruct	Mistral AI	1214	1206–1222	5.5K	$0.05 / $0.08
300	Jamba 1.5 Large	AI21 Labs	1213	1202–1223	3.3K	—
302	Reka Core	Reka	1212	1202–1222	3.1K	—
303	Gemma 2 27B IT	Google	1206	1201–1211	29.5K	$0.65 / $0.65
304	Amazon Nova Lite 1.0	Amazon	1205	1198–1212	7.8K	—
305	Nemotron-4 340B Instruct	NVIDIA	1203	1195–1211	7.4K	—
306	GLM-4	Z.ai	1203	1193–1213	3.8K	—
307	Hunyuan Standard 256K	Tencent	1202	1185–1219	1.1K	—
308	Phi-4	Microsoft	1201	1195–1208	9.2K	$0.07 / $0.14
309	GPT-4	OpenAI	1201	1194–1208	18.1K	$30 / $60
310	Llama 3.1 Nemotron 51B Instruct	NVIDIA	1201	1186–1215	1.5K	—
311	Claude 3 Sonnet	Anthropic	1199	1194–1205	38.8K	—
312	Gemini 1.5 Flash-8B	Google	1199	1193–1205	14.9K	—
313	Command R+	Cohere	1197	1187–1206	4K	$0.15 / $0.60
314	Aya Expanse 32B	Cohere	1196	1189–1203	11.3K	—
315	Llama 3 70B Instruct	Meta	1194	1189–1199	56.6K	—
316	Gemma 2 9B IT SimPO	Google	1191	1181–1201	3.7K	—
318	OLMo 2 32B Instruct	Ai2	1186	1169–1203	1.1K	—
319	Reka Flash	Reka	1185	1175–1195	3.2K	—
320	Qwen2-72B-Instruct	Alibaba	1181	1174–1188	14.2K	—
321	DeepSeek-Coder-V2	DeepSeek	1180	1171–1189	5.6K	—
323	Gemma 2 9B IT	Google	1178	1173–1183	21.4K	—
324	Llama 3.1 Tulu 3 8B	Ai2	1174	1159–1190	1.2K	—
325	Amazon Nova Micro 1.0	Amazon	1174	1167–1181	7.7K	—
326	Claude 3 Haiku	Anthropic	1173	1168–1179	43K	—
329	Ministral 8B	Mistral AI	1161	1148–1173	1.9K	$0.15 / $0.15
330	Llama 3.1 8B Instruct	Meta	1159	1153–1164	19.8K	$0.05 / $0.08
331	Qwen1.5-110B-Chat	Alibaba	1158	1150–1166	9.5K	—
333	Aya Expanse 8B	Cohere	1155	1145–1164	4K	—
334	Mistral Medium	Mistral AI	1152	1144–1160	11.5K	—
335	Jamba 1.5 Mini	AI21 Labs	1148	1137–1158	3.3K	—
336	Mixtral 8x22B Instruct v0.1	Mistral AI	1147	1141–1154	18.5K	—
337	Qwen1.5-72B-Chat	Alibaba	1141	1134–1149	13.8K	—
338	Yi 1.5 34B Chat	01.AI	1139	1132–1147	9K	—
339	InternLM2.5 20B Chat	—	1135	1125–1145	4.1K	—
340	Granite 3.1 8B Instruct	IBM	1131	1114–1147	1.3K	—
341	Reka Flash 21B	Reka	1129	1119–1140	5.6K	—
342	Llama 3 8B Instruct	Meta	1127	1121–1133	37.7K	—
345	GPT-3.5 Turbo	OpenAI	1119	1112–1125	23.5K	$1 / $2
346	Zephyr ORPO 141B A35B v0.1	—	1118	1102–1133	1.6K	—
347	Gemma 2 2B IT	Google	1118	1112–1123	18.2K	—
348	Granite 3.1 2B Instruct	IBM	1116	1100–1132	1.3K	—
349	Qwen1.5-32B-Chat	Alibaba	1116	1107–1124	7.7K	—
350	Gemini Pro	Google	1114	1104–1125	5.9K	$2 / $10
351	Phi-3 Medium 4K Instruct	Microsoft	1113	1106–1121	9.4K	—
352	DBRX Instruct Preview	—	1112	1103–1120	11.3K	—
353	Tulu 2 DPO 70B	—	1110	1096–1125	2K	—
355	Mixtral 8x7B Instruct v0.1	Mistral AI	1109	1103–1116	25K	—
356	Qwen1.5-14B-Chat	Alibaba	1102	1092–1112	6.2K	—
357	Starling LM 7B Beta	—	1096	1086–1106	5.8K	—
358	WizardLM 70B	Microsoft	1093	1080–1106	2.7K	—
360	Yi 34B Chat	01.AI	1091	1081–1100	5.1K	—
361	Llama 3.2 3B Instruct	Meta	1089	1078–1100	3.2K	$0.051 / $0.34
362	Granite 3.0 8B Instruct	IBM	1088	1076–1100	2.6K	—
363	Phi-3 Small 8K Instruct	Microsoft	1087	1078–1095	6.6K	—
364	DeepSeek LLM 67B Chat	DeepSeek	1079	1062–1096	1.5K	—
365	OpenChat 3.5	—	1076	1066–1087	4.4K	—
366	Llama 2 70B Chat	Meta	1071	1063–1078	12.6K	—
367	OpenHermes 2.5 Mistral 7B	Mistral AI	1070	1055–1085	1.6K	—
369	Starling LM 7B Alpha	—	1070	1059–1081	3.3K	—
370	Snowflake Arctic Instruct	Snowflake	1066	1058–1074	11.7K	—
371	Vicuna 33B	—	1065	1056–1074	7K	—
372	Llama 2 70B SteerLM Chat	NVIDIA	1060	1042–1078	1.1K	—
373	Mistral 7B Instruct v0.2	Mistral AI	1060	1051–1069	6.7K	—
374	Qwen1.5-7B-Chat	Alibaba	1058	1044–1072	1.7K	—
375	Phi-3 Mini 4K Instruct	Microsoft	1058	1048–1067	4.4K	—
376	Gemma 1.1 7B IT	Google	1057	1049–1065	8.9K	—
377	Nous Hermes 2 Mixtral 8x7B DPO	Nous Research	1056	1040–1072	1.4K	—
378	Granite 3.0 2B Instruct	IBM	1056	1043–1068	2.7K	—
379	MPT 30B Chat	—	1054	1033–1075	718	—
380	Dolphin 2.2.1 Mistral 7B	Mistral AI	1053	1029–1078	497	—
382	WizardLM 13B	Microsoft	1048	1035–1062	2K	—
383	Falcon 180B Chat	TII	1047	1019–1075	389	—
384	SOLAR 10.7B Instruct v1.0	Upstage	1046	1028–1065	1.2K	—
385	Llama 2 13B Chat	Meta	1045	1036–1055	6.1K	—
386	Vicuna 13B	—	1035	1026–1045	5.7K	—
387	Zephyr 7B Alpha	—	1034	1010–1059	534	—
388	Zephyr 7B Beta	—	1031	1019–1044	3.1K	—
389	Qwen-14B-Chat	Alibaba	1031	1015–1048	1.5K	—
390	Llama 3.2 1B Instruct	Meta	1031	1020–1042	3.2K	$0.027 / $0.20
391	SmolLM2 1.7B Instruct	—	1029	1008–1050	859	—
392	Code Llama 34B Instruct	Meta	1028	1015–1041	2.3K	—
393	Code Llama 70B Instruct	Meta	1024	994–1053	358	—
394	Phi-3 Mini 128K Instruct	Microsoft	1023	1013–1033	7.4K	—
395	Gemma 7B IT	Google	1017	1004–1030	2.8K	—
396	StripedHyena Nous 7B	—	1010	995–1025	1.7K	—
397	PaLM 2	Google	1010	997–1023	2.5K	—
398	Llama 2 7B Chat	Meta	1006	996–1016	4.5K	—
399	Mistral 7B Instruct	Mistral AI	1003	990–1017	2.8K	—
400	Vicuna 7B	—	994	980–1008	2K	—
401	Gemma 1.1 2B IT	Google	992	981–1003	3.9K	—
402	Guanaco 33B	—	991	971–1012	777	—
403	Qwen1.5-4B-Chat	Alibaba	978	966–991	2.6K	—
404	OLMo 7B Instruct	Ai2	978	963–994	1.9K	—
405	Gemma 2B IT	Google	970	954–986	1.5K	—
406	ChatGLM3 6B	—	954	936–972	1.3K	—
407	GPT4All 13B Snoozy	OpenAI	945	921–970	483	—
408	Koala 13B	—	944	929–959	1.9K	—
409	MPT 7B Chat	—	907	889–925	1.1K	—
410	ChatGLM2 6B	—	902	880–924	762	—
411	ChatGLM 6B	—	902	884–919	1.3K	—
412	Alpaca 13B	—	891	875–907	1.5K	—
413	OpenAssistant Pythia 12B	—	887	872–903	1.7K	—
414	RWKV-4 Raven 14B	—	883	866–899	1.4K	—
415	FastChat-T5 3B	—	858	840–876	1.1K	—
416	StableLM Tuned Alpha 7B	—	831	811–851	814	—
417	Dolly 2.0 12B	—	814	793–834	899	—
418	LLaMA 13B	Meta	781	757–805	584	—

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.

Full leaderboard

Related leaderboards