OnlySOTA

Arena — Text

As Arena publishes it — their metrics, their models. Follow a model name to its page upstream.

Published by
Arena
Licence
not stated
Updates
continuous
Data as of
2026-08-21
Fetched
2026-08-22
Entries
394 · 216 unmatched
Top 12 by Overall (style control), one row per model
  1. Claude Fable 5 (Opus 4.8 fallback) 1508
  2. Claude Opus 4.6 1504
  3. Claude Opus 4.7 1502
  4. Muse Spark 1.2 1498
  5. Claude Opus 5 1493
  6. Muse Spark 1.1 1491
  7. Gemini 3.7 Flash 1490
  8. Kimi K3 1489
  9. Muse Spark 1488
  10. GLM-5.3 1487
  11. Gemini 3.1 Pro Preview 1486
  12. Gemini 3 Pro Preview 1485

An Elo has no zero — it is an arbitrary anchor, not "no skill" — so a bar drawn from it would encode the anchor. Each row is a dot on a range beginning at 1483; the distance between rows is the reading, the distance from the left edge is not.

394 scored

#Model
1Claude Fable 5 (Opus 4.8 fallback)anthropic15081503–1513
2Claude Opus 4.6highanthropic15041501–1508
3Claude Opus 4.7highanthropic15021498–1506
4Muse Spark 1.2xhighmeta14981487–1508
5Claude Opus 4.6anthropic14971494–1501
6Claude Opus 4.7anthropic14941490–1498
7Claude Opus 5highanthropic14931488–1497
8Muse Spark 1.1meta14911485–1496
9Gemini 3.7 Flashhighgoogle14901482–1498
10Kimi K3maxkimi14891483–1495
11Muse Sparkmeta14881482–1494
12Claude Opus 5maxanthropic14871481–1494
13GLM-5.3maxzai14871477–1497
14Gemini 3.1 Pro Previewgoogle14861483–1490
15Gemini 3 Pro Previewgoogle14851482–1489
16GPT-5.6 Solxhighopenai14821477–1488
17GPT-5.5highopenai14821478–1486
18Claude Opus 4.8highanthropic14821477–1486
19Unknown developerUDqwen3.8-maxmaxUnmatched14811474–1488
20Gemini 3.6 Flashhighgoogle14811475–1486
21Gemini 3.5 Flashhighgoogle14781474–1483
22GPT-5.4highopenai14761473–1480
23GPT-5.5openai14761472–1480
24Unknown developerUDgpt-5.2-chat-latest-20260210Unmatched14761472–1480
25Unknown developerUDgrok-4.20-beta1Unmatched14751470–1479
26Gemini 3.5 Flashmediumgoogle14741469–1479
27Unknown developerUDqwen3.7-max-previewUnmatched14741464–1484
28Unknown developerUDgpt-5.5-instantUnmatched14741468–1479
29Claude Opus 4.8anthropic14731468–1477
30Gemini 3 Flash Previewgoogle14731468–1477
31Unknown developerUDclaude-opus-4-5-20251101-high-32kUnmatched14731469–1477
32Claude Sonnet 4.6anthropic14721468–1476
33Unknown developerUDgrok-4.20-beta-0309-reasoningonUnmatched14721468–1475
34GLM-5.2maxzai14701466–1475
35Grok 4.5xai14701465–1475
36Unknown developerUDgrok-4.20-multi-agent-beta-0309Unmatched14701466–1474
37Unknown developerUDclaude-opus-4-5-20251101Unmatched14691466–1472
38Unknown developerUDernie-5.1Unmatched14681463–1473
39GLM-5.1zai14681464–1472
40MiMo-V2.5-Proxiaomi14681464–1472
41GPT-5.4openai14661462–1470
42Unknown developerUDgrok-4.1-thinkingonUnmatched14661462–1469
43Unknown developerUDqwen3.5-max-previewUnmatched14651460–1470
44GPT-5.6 Terraxhighopenai14651460–1471
45Claude Sonnet 5highanthropic14611456–1466
46Grok 4.6highxai14611451–1471
47Kimi K2.6kimi14611456–1465
48Unknown developerUDqwen3.6-max-previewUnmatched14601452–1468
49Unknown developerUDgrok-4.1Unmatched14591456–1463
50Unknown developerUDdeepseek-v4-pro-high-20260813Unmatched14591450–1469
51Gemini 3 Flash Previewon · minimalgoogle14581455–1461
52DeepSeek V4 Pro 0813deepseek14581454–1462
53Qwen3.7 Plusalibaba14571453–1462
54Gemini 3.5 Flash-Litegoogle14571452–1463
55GLM-5zai14571452–1461
56Hy3tencent14571449–1465
57Unknown developerUDdola-seed-2.0-proUnmatched14561452–1459
58Unknown developerUDclaude-sonnet-4-5-20250929-high-32kUnmatched14561453–1459
59Unknown developerUDdeepseek-v4-pro-high-previewUnmatched14551451–1459
60Unknown developerUDclaude-sonnet-4-5-20250929Unmatched14551452–1458
61GPT-5.1highopenai14551451–1458
62Gemma 4 31Bgoogle14511444–1459
63GPT-5.6 Lunaxhighopenai14511446–1456
64Kimi K2.5onkimi14501447–1453
65Unknown developerUDernie-5.0-preview-1203Unmatched14491442–1455
66Unknown developerUDclaude-opus-4-1-20250805-thinking-16kUnmatched14491445–1452
67Unknown developerUDgpt-5.3-chat-latestUnmatched14491444–1453
68MiMo-V2-Proxiaomi14491444–1453
69GPT-5.4 minihighopenai14481444–1452
70Unknown developerUDclaude-opus-4-1-20250805Unmatched14471444–1450
71Unknown developerUDernie-5.0-0110Unmatched14461442–1450
72Gemini 2.5 Progoogle14451443–1448
73Unknown developerUDgpt-4.5-preview-2025-02-27Unmatched14451439–1450
74Qwen3.6 Plusalibaba14431439–1448
75GPT-4o (March 2025, chatgpt-4o-latest)openai14431440–1446
76MiniMax-M3minimax14431438–1447
77Grok 4.3xai14421438–1446
78Qwen3.5 397B A17Balibaba14421438–1445
79GLM-4.7zai14421435–1448
80Inklingthinking-machines14401435–1445
81Unknown developerUDqwen3.8-27bUnmatched14401429–1450
82GPT-5.1openai14391435–1442
83Unknown developerUDdeepseek-v4-flash-high-previewUnmatched14381434–1442
84Gemma 4 26B A4Bgoogle14381431–1446
85GPT-5.2highopenai14381434–1441
86Unknown developerUDdeepseek-v4-flashUnmatched14361431–1440
87Unknown developerUDlongcat-flash-chat-2602-expUnmatched14351431–1440
88GPT-5.2openai14351432–1439
89Qwen3 Max (Preview)alibaba14341430–1439
90GPT-5highopenai14341430–1439
91MiMo-V2.5xiaomi14341429–1438
92GLM 5V Turbozai14331426–1440
93Gemini 3.1 Flash-Litegoogle14321428–1436
94Unknown developerUDkimi-k2.5-instantUnmatched14311424–1438
95Unknown developerUDo3-2025-04-16Unmatched14311427–1434
96Grok 4.1 Fastonxai14311427–1434
97MiMo-V2-Omnixiaomi14301424–1436
98Kimi K2 Thinkingkimi14301427–1433
99Mistral Medium 3.5mistral14271420–1433
100Unknown developerUDgpt-5-chatUnmatched14271422–1431
101Muse Glimmermeta14261416–1436
102Nemotron 3 Ultra 550B A55Bnvidia14261419–1433
103Unknown developerUDamazon-nova-experimental-chat-26-02-10Unmatched14261416–1435
104DeepSeek V3.2deepseek14251422–1429
105Unknown developerUDclaude-opus-4-20250514-thinking-16kUnmatched14251421–1429
106DeepSeek V3.2 Expondeepseek14251418–1431
107GLM-4.6zai14241420–1428
108Unknown developerUDqwen3-max-2025-09-23Unmatched14241417–1430
109Qwen3 235B A22B 2507 Instructalibaba14231420–1425
110DeepSeek V3.2ondeepseek14231419–1426
111DeepSeek V3.2 Expdeepseek14231416–1429
112DeepSeek R1 0528 (May '25)deepseek14221416–1427
113Unknown developerUDgrok-4-fast-chatUnmatched14201412–1428
114Unknown developerUDernie-5.0-preview-1022Unmatched14181409–1427
115Unknown developerUDkimi-k2-0711-previewUnmatched14181413–1423
116Kimi K2 0905kimi14181411–1424
117DeepSeek V3.1deepseek14171411–1423
118DeepSeek V3.1 Terminusondeepseek14171407–1427
119Qwen3.5 122B A10Balibaba14171413–1421
120DeepSeek V3.1ondeepseek14161410–1423
121MiniMax-M2.7minimax14161413–1420
122Unknown developerUDamazon-nova-experimental-chat-26-01-10Unmatched14151405–1425
123DeepSeek V3.1 Terminusdeepseek14151405–1424
124Qwen3 VL 235B A22B Instructalibaba14141408–1421
125Mistral Large 3mistral14141411–1417
126Unknown developerUDgpt-4.1-2025-04-14Unmatched14141410–1418
127Unknown developerUDclaude-haiku-4-5-20251001Unmatched14131410–1416
128Unknown developerUDclaude-opus-4-20250514Unmatched14131408–1417
129Hy3-previewtencent14121405–1420
130Unknown developerUDgrok-3-preview-02-24Unmatched14111407–1416
131GLM-4.5zai14111406–1416
132Gemini 2.5 Flashgoogle14101408–1412
133Unknown developerUDgrok-4-0709Unmatched14091405–1413
134Unknown developerUDmistral-medium-2508Unmatched14091406–1411
135Qwen3.5 27Balibaba14081403–1412
136Inkling Smallthinking-machines14051398–1411
137Gemini 2.5 Flash Preview (Sep '25)google14041400–1408
138Grok 4 Fastonxai14041399–1409
139Qwen3 235B A22Boffalibaba14021398–1407
140Unknown developerUDo1-2024-12-17Unmatched14021398–1407
141GPT-5.4 nanohighopenai14021398–1406
142Unknown developerUDlongcat-flash-chatUnmatched14011394–1407
143Qwen3 Next 80B A3B Instructalibaba14011396–1405
144Unknown developerUDclaude-sonnet-4-20250514-thinking-32kUnmatched14001395–1404
145Qwen3 235B A22B 2507alibaba13991392–1405
146DeepSeek R1 0528 (May '25)deepseek13981393–1403
147Unknown developerUDqwen3.5-flashUnmatched13971393–1401
148DeepSeek V3 0324deepseek13961392–1399
149Qwen3.5 35B A3Balibaba13951391–1400
150Unknown developerUDhunyuan-vision-1.5-thinkingonUnmatched13951383–1407
151Qwen3 VL 235B A22Bonalibaba13951388–1402
152Step 3.5 Flashstepfun13941391–1398
153Unknown developerUDamazon-nova-experimental-chat-12-10Unmatched13931384–1403
154MiMo-V2-Flashoffxiaomi13921389–1396
155MiniMax-M2.5minimax13901386–1394
156Unknown developerUDo4-mini-2025-04-16Unmatched13901386–1394
157GPT-5 minihighopenai13901385–1394
158Unknown developerUDclaude-sonnet-4-20250514Unmatched13901385–1394
159o1-previewopenai13891384–1394
160Unknown developerUDclaude-3-7-sonnet-20250219-thinking-32kUnmatched13881384–1392
161Qwen3 Coder 480B A35B Instructalibaba13881383–1393
162Unknown developerUDmistral-medium-2505Unmatched13871382–1392
163Unknown developerUDhunyuan-t1-20250711Unmatched13871378–1395
164MiMo-V2-Flashonxiaomi13861380–1393
165Unknown developerUDminimax-m2.1-previewUnmatched13841379–1389
166Qwen3 30B A3B 2507 Instructalibaba13831378–1388
167Unknown developerUDgpt-4.1-mini-2025-04-14Unmatched13831378–1387
168Unknown developerUDhunyuan-turbos-20250416Unmatched13831376–1389
169Gemini 2.5 Flash-Lite Preview (Sep '25)offgoogle13801376–1383
170Unknown developerUDtrinity-large-previewUnmatched13791374–1383
171GLM-4.6Vzai13771366–1388
172Solar Pro 4upstage13761363–1388
173Qwen3 235B A22Balibaba13751370–1379
174Unknown developerUDgemini-2.5-flash-lite-preview-06-17-thinkingonUnmatched13751370–1379
175Unknown developerUDqwen2.5-maxmaxUnmatched13741370–1378
176Unknown developerUDclaude-3-5-sonnet-20241022Unmatched13741371–1377
177GLM-4.5-Airzai13731368–1377
178Unknown developerUDclaude-3-7-sonnet-20250219Unmatched13721368–1376
179Trinity Large Thinkingarcee13691364–1374
180Qwen3 Next 80B A3Bonalibaba13691363–1375
181GLM-4.7-Flashzai13671361–1373
182Gemma 3 27B Instructgoogle13661362–1370
183Unknown developerUDamazon-nova-experimental-chat-11-10Unmatched13661361–1370
184o3-minihighopenai13641358–1369
185Unknown developerUDminimax-m1Unmatched13631359–1367
186Grok 3 mini Reasoninghighxai13621356–1367
187Nemotron 3 Super 120B A12Bnvidia13601353–1368
188Unknown developerUDgemini-2.0-flash-001Unmatched13601356–1364
189DeepSeek V3 (Dec '24)deepseek13581354–1363
190Mistral Small 3.2mistral13571352–1362
191Unknown developerUDgrok-3-mini-betaUnmatched13561351–1361
192INTELLECT-3prime-intellect13561347–1364
193Unknown developerUDcommand-a-03-2025Unmatched13541350–1357
194Unknown developerUDgemini-2.0-flash-lite-preview-02-05Unmatched13541349–1358
195GLM-4.5Vzai13531345–1362
196gpt-oss-120bopenai13521348–1357
197Unknown developerUDgemini-1.5-pro-002Unmatched13511348–1355
198Unknown developerUDamazon-nova-experimental-chat-10-20Unmatched13491343–1355
199Unknown developerUDhunyuan-turbos-20250226Unmatched13491337–1361
200Unknown developerUDnvidia-nemotron-3.5-lightning-30b-a3b-nvfp4Unmatched13481338–1359
201Unknown developerUDstep-3Unmatched13481341–1356
202o3-miniopenai13481344–1351
203Llama 3.1 Nemotron Ultra 253B v1nvidia13471336–1359
204Unknown developerUDamazon-nova-experimental-chat-10-09Unmatched13471336–1358
205Qwen3 32Balibaba13471338–1356
206Mercury 2inception13471336–1357
207Unknown developerUDqwen-plus-0125Unmatched13461338–1354
208GPT-4o (May '24)openai13461343–1349
209Ling-flash-2.0inclusionai13461339–1353
210MiniMax-M2minimax13461338–1353
211Llama Nemotron Super 49B v1.5nvidia13431333–1353
212Claude 3.5 Sonnet (June '24)anthropic13431340–1346
213Unknown developerUDglm-4-plus-0111Unmatched13431334–1351
214Unknown developerUDgemma-3-12b-itUnmatched13421332–1351
215Unknown developerUDhunyuan-turbo-0110Unmatched13411329–1352
216GPT-5 nanohighopenai13371331–1344
217o1-miniopenai13371333–1341
218Unknown developerUDgemini-advanced-0514Unmatched13361331–1341
219Unknown developerUDgrok-2-2024-08-13Unmatched13361332–1339
220QwQ 32Balibaba13361331–1340
221Unknown developerUDnova-2-liteUnmatched13361330–1342
222GPT-4o (Aug '24)openai13351331–1340
223Unknown developerUDllama-3.1-405b-instruct-bf16Unmatched13351331–1339
224Unknown developerUDstep-2-16k-exp-202412Unmatched13341325–1342
225Unknown developerUDllama-3.1-405b-instruct-fp8Unmatched13331330–1337
226Molmo2-8Bai213301308–1351
227Olmo 3.1 32B Instructai213291323–1335
228Unknown developerUDyi-lightningUnmatched13281323–1333
229Llama 3.3 Nemotron Super 49B v1nvidia13281316–1340
230Llama 4 Maverickmeta13271323–1331
231Qwen3 30B A3Balibaba13271322–1332
232Unknown developerUDhunyuan-large-2025-02-10Unmatched13261317–1336
233Unknown developerUDgpt-4-turbo-2024-04-09Unmatched13241320–1328
234Unknown developerUDclaude-3-5-haiku-20241022Unmatched13241321–1327
235Unknown developerUDgemini-1.5-pro-001Unmatched13241320–1328
236DeepSeek-V2.5 (Dec '24)deepseek13231315–1332
237Llama 4 Scoutmeta13221318–1327
238Unknown developerUDgpt-4.1-nano-2025-04-14Unmatched13221314–1330
239Unknown developerUDclaude-3-opus-20240229Unmatched13221319–1325
240Ring-flash-2.0inclusionai13201313–1327
241Unknown developerUDstep-1o-turbo-202506Unmatched13201313–1327
242Unknown developerUDglm-4-plusUnmatched13191314–1324
243Llama 3.3 70B Instructmeta13181315–1322
244Gemma 3n E4B Instructgoogle13181313–1323
245Unknown developerUDqwen-max-0919Unmatched13181312–1324
246Unknown developerUDgpt-4o-mini-2024-07-18Unmatched13181314–1321
247gpt-oss-20bopenai13181311–1324
248NVIDIA Nemotron 3 Nano 30B A3Bnvidia13151309–1320
249Unknown developerUDqwen2.5-plus-1127Unmatched13151308–1321
250Mistral Large 2 (Jul '24)mistral13141310–1318
251Unknown developerUDathene-v2-chatUnmatched13141310–1319
252Unknown developerUDgpt-4-0125-previewUnmatched13131309–1317
253Unknown developerUDgpt-4-1106-previewUnmatched13131309–1317
254Unknown developerUDhunyuan-standard-2025-02-10Unmatched13111302–1321
255Unknown developerUDgemini-1.5-flash-002Unmatched13091305–1313
256Unknown developerUDgrok-2-mini-2024-08-13Unmatched13081305–1312
257DeepSeek-V2.5deepseek13071302–1312
258Unknown developerUDathene-70b-0725Unmatched13071301–1312
259Unknown developerUDmercuryUnmatched13061292–1320
260Granite 4.1 8Bibm13061295–1316
261Mistral Large 2 (Nov '24)mistral13051301–1310
262Olmo 3 32B Thinkai213051297–1313
263Unknown developerUDmagistral-medium-2506Unmatched13041298–1311
264Unknown developerUDmistral-small-3.1-24b-instruct-2503Unmatched13041299–1308
265Unknown developerUDgemma-3-4b-itUnmatched13031294–1313
266Qwen2.5 Instruct 72Balibaba13031299–1307
267Unknown developerUDllama-3.1-nemotron-70b-instructUnmatched12991291–1307
268Unknown developerUDhunyuan-large-visionUnmatched12941285–1303
269Unknown developerUDllama-3.1-70b-instructUnmatched12931290–1297
270Unknown developerUDamazon-nova-pro-v1.0Unmatched12901286–1295
271Unknown developerUDjamba-1.5-largeUnmatched12891282–1297
272Unknown developerUDgemma-2-27b-itUnmatched12891286–1293
273Unknown developerUDreka-core-20240904Unmatched12881281–1295
274Unknown developerUDgpt-4-0314Unmatched12871283–1292
275Unknown developerUDibm-granite-h-smallUnmatched12871279–1296
276Unknown developerUDgemini-1.5-flash-001Unmatched12861282–1291
277Unknown developerUDllama-3.1-nemotron-51b-instructUnmatched12861276–1296
278Unknown developerUDllama-3.1-tulu-3-70bUnmatched12861276–1297
279Olmo 3.1 32B Thinkai212851278–1292
280Unknown developerUDclaude-3-sonnet-20240229Unmatched12811277–1285
281Unknown developerUDgemma-2-9b-it-simpoUnmatched12801273–1287
282Unknown developerUDnemotron-4-340b-instructUnmatched12771272–1282
283Unknown developerUDllama-3-70b-instructUnmatched12761273–1280
284Unknown developerUDcommand-r-plus-08-2024Unmatched12761270–1283
285Unknown developerUDgpt-4-0613Unmatched12761272–1280
286Mistral Small 3mistral12741268–1280
287Unknown developerUDglm-4-0520Unmatched12731266–1280
288Unknown developerUDreka-flash-20240904Unmatched12721265–1279
289Qwen2.5 Coder Instruct 32Balibaba12711262–1279
290Unknown developerUDc4ai-aya-expanse-32bUnmatched12671262–1272
291Unknown developerUDgemma-2-9b-itUnmatched12671263–1271
292DeepSeek-Coder-V2deepseek12651259–1271
293Qwen2 Instruct 72Balibaba12621257–1266
294Unknown developerUDcommand-r-plusUnmatched12611257–1266
295Unknown developerUDclaude-3-haiku-20240307Unmatched12611258–1265
296Unknown developerUDamazon-nova-lite-v1.0Unmatched12601255–1266
297Unknown developerUDgemini-1.5-flash-8b-001Unmatched12591254–1263
298microsoftMiPhi-4microsoft12561252–1261
299OLMo 2 32Bai212511241–1262
300Unknown developerUDcommand-r-08-2024Unmatched12501244–1257
301Unknown developerUDmistral-large-2402Unmatched12421237–1247
302Unknown developerUDamazon-nova-micro-v1.0Unmatched12411236–1246
303Unknown developerUDjamba-1.5-miniUnmatched12401232–1247
304Unknown developerUDministral-8b-2410Unmatched12381228–1247
305Gemini 1.0 Progoogle12361229–1244
306Qwen1.5 Chat 110Balibaba12341228–1239
307Unknown developerUDreka-flash-21b-20240226-onlineUnmatched12331226–1241
308Unknown developerUDhunyuan-standard-256kUnmatched12331222–1245
309Unknown developerUDqwen1.5-72b-chatUnmatched12331228–1238
310Mixtral 8x22B Instructmistral12291225–1234
311Unknown developerUDcommand-rUnmatched12271222–1231
312Unknown developerUDreka-flash-21b-20240226Unmatched12271221–1232
313Unknown developerUDgpt-3.5-turbo-0125Unmatched12251220–1230
314Unknown developerUDllama-3-8b-instructUnmatched12231220–1227
315Unknown developerUDgemini-proUnmatched12231211–1235
316Unknown developerUDc4ai-aya-expanse-8bUnmatched12231216–1230
317Mistral Mediummistral12221217–1228
318Unknown developerUDllama-3.1-tulu-3-8bUnmatched12201210–1231
319Unknown developerUDyi-1.5-34b-chatUnmatched12131208–1218
320Unknown developerUDzephyr-orpo-141b-A35b-v0.1Unmatched12131202–1223
321Unknown developerUDllama-3.1-8b-instructUnmatched12111207–1215
322Unknown developerUDgranite-3.1-8b-instructUnmatched12081197–1219
323Unknown developerUDqwen1.5-32b-chatUnmatched12041198–1210
324Unknown developerUDgpt-3.5-turbo-1106Unmatched12041195–1212
325Unknown developerUDgemma-2-2b-itUnmatched12001196–1204
326Unknown developerUDphi-3-medium-4k-instructUnmatched11981192–1203
327Mixtral 8x7B Instructmistral11971193–1201
328Unknown developerUDdbrx-instruct-previewUnmatched11951189–1201
329Unknown developerUDqwen1.5-14b-chatUnmatched11911184–1198
330Unknown developerUDinternlm2_5-20b-chatUnmatched11911184–1198
331DeepSeek LLM 67B Chat (V1)deepseek11841173–1196
332Unknown developerUDwizardlm-70bUnmatched11841175–1194
333Unknown developerUDyi-34b-chatUnmatched11831177–1190
334Unknown developerUDgranite-3.0-8b-instructUnmatched11831174–1191
335Unknown developerUDopenchat-3.5Unmatched11831173–1192
336Unknown developerUDopenchat-3.5-0106Unmatched11821174–1190
337Unknown developerUDgemma-1.1-7b-itUnmatched11821176–1188
338Unknown developerUDsnowflake-arctic-instructUnmatched11801174–1186
339Unknown developerUDgranite-3.1-2b-instructUnmatched11791167–1190
340Unknown developerUDtulu-2-dpo-70bUnmatched11771168–1187
341Unknown developerUDopenhermes-2.5-mistral-7bUnmatched11761165–1186
342Unknown developerUDvicuna-33bUnmatched11731166–1179
343Unknown developerUDstarling-lm-7b-betaUnmatched11711163–1178
344Unknown developerUDphi-3-small-8k-instructUnmatched11711165–1177
345Llama 2 Chat 70Bmeta11701165–1176
346Unknown developerUDstarling-lm-7b-alphaUnmatched11671159–1175
347Unknown developerUDllama-3.2-3b-instructUnmatched11671159–1174
348Unknown developerUDnous-hermes-2-mixtral-8x7b-dpoUnmatched11641152–1176
349Unknown developerUDgranite-3.0-2b-instructUnmatched11561148–1165
350QwQ 32B-Previewalibaba11541143–1166
351Unknown developerUDllama2-70b-steerlm-chatUnmatched11541142–1167
352Unknown developerUDsolar-10.7b-instruct-v1.0Unmatched11521139–1165
353Unknown developerUDdolphin-2.2.1-mistral-7bUnmatched11521137–1167
354Unknown developerUDmpt-30b-chatUnmatched11501138–1163
355Unknown developerUDwizardlm-13bUnmatched11491140–1158
356Unknown developerUDmistral-7b-instruct-v0.2Unmatched11491142–1156
357Unknown developerUDfalcon-180b-chatUnmatched11481131–1165
358Unknown developerUDqwen1.5-7b-chatUnmatched11441134–1153
359Unknown developerUDphi-3-mini-4k-instruct-june-2024Unmatched11431136–1149
360Llama 2 Chat 13Bmeta11411134–1148
361Unknown developerUDvicuna-13bUnmatched11411134–1148
362Qwen Chat 14Balibaba11391128–1150
363PALM-2google11391129–1148
364Unknown developerUDgemma-7b-itUnmatched11371128–1147
365Unknown developerUDcodellama-34b-instructUnmatched11371128–1145
366Unknown developerUDzephyr-7b-betaUnmatched11311122–1139
367Phi-3 Mini Instruct 3.8Bazure11291122–1137
368Unknown developerUDphi-3-mini-4k-instructUnmatched11281121–1134
369Unknown developerUDguanaco-33bUnmatched11271115–1139
370Unknown developerUDzephyr-7b-alphaUnmatched11271111–1142
371Unknown developerUDstripedhyena-nous-7bUnmatched11211110–1132
372Unknown developerUDcodellama-70b-instructUnmatched11191101–1137
373Unknown developerUDgemma-1.1-2b-itUnmatched11161109–1124
374Unknown developerUDvicuna-7bUnmatched11151106–1124
375Unknown developerUDsmollm2-1.7b-instructUnmatched11141100–1129
376Unknown developerUDllama-3.2-1b-instructUnmatched11111103–1119
377Mistral 7B Instructmistral11101101–1119
378Llama 2 Chat 7Bmeta11081101–1115
379Unknown developerUDgemma-2b-itUnmatched10931082–1105
380Unknown developerUDqwen1.5-4b-chatUnmatched10911081–1100
381Unknown developerUDolmo-7b-instructUnmatched10731062–1085
382Unknown developerUDkoala-13bUnmatched10711061–1080
383Unknown developerUDalpaca-13bUnmatched10691058–1081
384Unknown developerUDgpt4all-13b-snoozyUnmatched10671052–1082
385Unknown developerUDmpt-7b-chatUnmatched10631051–1075
386Unknown developerUDchatglm3-6bUnmatched10561044–1068
387Unknown developerUDRWKV-4-Raven-14BUnmatched10421030–1053
388Unknown developerUDchatglm2-6bUnmatched10241011–1038
389Unknown developerUDoasst-pythia-12bUnmatched10231012–1034
390Unknown developerUDchatglm-6bUnmatched995983–1008
391Unknown developerUDfastchat-t5-3bUnmatched992980–1004
392Unknown developerUDdolly-v2-12bUnmatched982968–995
393Unknown developerUDllama-13bUnmatched974959–990
394Unknown developerUDstablelm-tuned-alpha-7bUnmatched953940–965

What the columns measure

Overall (style control)
Higher is better · General preference