LMArena Text: longer queries leaderboard
- Gemini 4 Argon leads
- 1547
- models measured
- 156
- lead over #2
- +15 Elo
- median
- 1414
Leader on LMArena Text: longer queries · read October 21
On October 21, 2026, 156 of our catalog's models had a LMArena Text: longer queries result, and Google Gemini 4 Argon led with 1547.
The longer prompts in the arena. People ask a question, compare two anonymous answers and vote for the better one; the rating is built from those votes, as LMArena publishes it.
Role in the index
We collect this benchmark and show it as supporting evidence. It is not part of the Vibe Coding Index, because it measures something other than coding and the index is about coding. Read the methodology
| # | Model | Result | Votes | Interval (±) | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|---|---|
| 1 | Gemini 4 ArgonGoogle | 1547 | 2,063 | ±13.6 | 80.5 | $10.00 | |
| 2 | Claude Opus 5.5Anthropic | 1532 | 4,043 | ±10.4 | 92.2 | $20.00 | |
| 3 | Claude Fable 5.1Anthropic | 1524 | 6,456 | ±8.3 | 89.1 | $50.00 | |
| 4 | Claude Opus 4.6Anthropic | 1518 | 35,006 | ±4.7 | 66.9 | $25.00 | |
| 5 | Claude Opus 5Anthropic | 1517 | 15,833 | ±6.2 | 81.8 | $25.00 | |
| 6 | Claude Fable 5Anthropic | 1510 | 20,128 | ±5.6 | 82.1 | $50.00 | |
| 7 | Gemini 3.8 FlashGoogle | 1507 | 19,059 | ±6.0 | 70.5 | $4.125 | |
| 8 | Claude Opus 4.7Anthropic | 1505 | 30,103 | ±5.1 | 51.1 | $25.00 | |
| 9 | MiMo-V2.6-ProXiaomi | 1501 | 1,648 | ±14.6 | 72.6 | $0.87 | |
| 10 | Claude Sonnet 5.5Anthropic | 1495 | 3,434 | ±10.9 | 88.9 | $10.00 | |
| 11 | Kimi K3Moonshot AI | 1494 | 14,884 | ±6.1 | 61.8 | $11.936 | |
| 12 | Muse WonderMeta | 1493 | 2,257 | ±12.9 | 64.5 | $20.00 | |
| 13 | Gemini 3.7 FlashGoogle | 1492 | 13,535 | ±6.5 | 69.9 | $3.75 | |
| 14 | Qwen3.8 Max (0902)Qwen | 1488 | 13,032 | ±6.4 | 63.5 | $6.00 | |
| 15 | Muse Spark 1.3Meta | 1488 | 8,715 | ±7.4 | 79.7 | $4.25 | |
| 16 | GPT-5.5OpenAI | 1484 | 32,009 | ±5.0 | 67.8 | $30.00 | |
| 17 | Claude Opus 4.8Anthropic | 1483 | 30,196 | ±5.1 | 66.0 | $25.00 | |
| 18 | GLM 5.3Z.ai | 1483 | 10,923 | ±6.8 | 73.1 | $1.40 | |
| 19 | Gemini 3.5 FlashGoogle | 1483 | 22,814 | ±5.3 | 42.8 | $9.00 | |
| 20 | Gemini 3.1 Pro PreviewGoogle | 1482 | 57,242 | ±4.1 | 35.3 | $12.00 | |
| 21 | GLM 5.3 FlashZ.ai | 1481 | 15,938 | ±6.3 | 71.0 | $0.50 | |
| 22 | MiMo-V2.5-ProXiaomi | 1481 | 34,292 | ±4.8 | 40.0 | $0.609 | |
| 23 | GPT-5.6 SolOpenAI | 1481 | 19,254 | ±5.7 | 76.7 | $20.00 | |
| 24 | GLM 5.2Z.ai | 1480 | 23,394 | ±5.3 | 57.7 | $7.00 | |
| 25 | Claude Opus 4.5Anthropic | 1479 | 24,244 | ±4.9 | 66.8 | $25.00 | |
| 26 | Claude Sonnet 4.6Anthropic | 1479 | 31,084 | ±4.9 | 57.8 | $15.00 | |
| 27 | Claude Sonnet 4.5Anthropic | 1475 | 26,471 | ±4.6 | 59.1 | $15.00 | |
| 28 | Gemini 3.6 FlashGoogle | 1475 | 17,142 | ±5.9 | 48.3 | $3.75 | |
| 29 | DeepSeek V4.1 FlashDeepSeek | 1473 | 5,836 | ±8.4 | 77.2 | $0.525 | |
| 30 | GPT-5.4OpenAI | 1473 | 28,436 | ±5.2 | 37.7 | $15.00 | |
| 31 | Muse Spark 1.2Meta | 1473 | 4,199 | ±9.8 | 65.1 | $4.25 | |
| 32 | Kimi K2.6Moonshot AI | 1468 | 16,958 | ±6.0 | 44.2 | $3.41 | |
| 33 | GLM 5.1Z.ai | 1467 | 28,988 | ±4.8 | 44.0 | $4.40 | |
| 34 | Claude Sonnet 5Anthropic | 1462 | 23,486 | ±5.3 | 63.5 | $10.00 | |
| 35 | Muse Spark 1.1Meta | 1462 | 20,636 | ±5.5 | 48.9 | $4.25 | |
| 36 | Grok 4.5xAI | 1462 | 19,271 | ±5.7 | 75.5 | $6.00 | |
| 37 | GPT-6 AstraOpenAI | 1460 | 5,537 | ±8.7 | 88.7 | $50.00 | |
| 38 | MiMo-V2.6-FlashXiaomi | 1459 | 5,153 | ±9.0 | 61.9 | $0.28 | |
| 39 | GPT-6.1 SolOpenAI | 1458 | 2,980 | ±11.6 | 88.7 | $10.00 | |
| 40 | DeepSeek V4 Pro 0423DeepSeek | 1458 | 25,924 | ±5.3 | 35.3 | $1.9105 | |
| 41 | DeepSeek V4 Pro 0813DeepSeek | 1458 | 4,568 | ±9.2 | 54.6 | $1.98 | |
| 42 | Grok 4.6xAI | 1456 | 14,242 | ±6.3 | 76.4 | $6.00 | |
| 43 | Claude Opus 4.1Anthropic | 1455 | 11,491 | ±6.0 | 27.2 | $75.00 | |
| 44 | Qwen3.7 PlusQwen | 1454 | 19,522 | ±5.6 | Not benchmarked | $1.28 | |
| 45 | GPT-5.6 TerraOpenAI | 1454 | 20,928 | ±5.6 | 69.0 | $12.00 | |
| 46 | Gemini 2.5 ProGoogle | 1449 | 34,001 | ±3.9 | 37.0 | $10.00 | |
| 47 | Step 5 PreviewStepFun | 1449 | 3,705 | ±10.2 | 71.4 | $2.70 | |
| 48 | Qwen3.8 27BQwen | 1448 | 11,101 | ±6.8 | 73.6 | $1.35 | |
| 49 | GPT-5.1OpenAI | 1448 | 10,938 | ±6.3 | 53.3 | $10.00 | |
| 50 | Gemma 4 31BGoogle | 1446 | 1,797 | ±13.4 | 38.3 | $0.40 | |
| 51 | MiniMax M3MiniMax | 1446 | 29,633 | ±5.0 | 57.8 | $1.20 | |
| 52 | GLM 5Z.ai | 1446 | 11,115 | ±6.3 | 59.7 | $3.20 | |
| 53 | MiMo-V2.5Xiaomi | 1445 | 21,277 | ±5.7 | 34.0 | $0.238 | |
| 54 | Kimi K2.5Moonshot AI | 1445 | 29,803 | ±4.7 | 58.5 | $2.50 | |
| 55 | Hy3Tencent | 1442 | 5,770 | ±8.4 | 43.9 | $0.528 | |
| 56 | Qwen3.5 397B A17BQwen | 1441 | 41,898 | ±4.3 | 28.6 | $2.34 | |
| 57 | Qwen3.6 PlusQwen | 1439 | 21,155 | ±5.6 | 37.4 | $1.95 | |
| 58 | GLM 5V TurboZ.ai | 1438 | 4,901 | ±9.0 | 28.8 | $4.00 | |
| 59 | Nemotron 3 UltraNVIDIA | 1437 | 5,321 | ±8.9 | Not benchmarked | $2.40 | |
| 60 | GPT-5.6 LunaOpenAI | 1436 | 19,340 | ±5.7 | 61.5 | $1.20 | |
| 61 | Gemini 3.5 Flash LiteGoogle | 1435 | 17,104 | ±6.0 | 33.6 | $2.50 | |
| 62 | T InklingThinking Machines | 1435 | 19,895 | ±5.6 | 49.7 | $4.05 | |
| 63 | DeepSeek V4 Flash 0423DeepSeek | 1434 | 23,342 | ±5.5 | 54.6 | $0.182 | |
| 64 | GLM 4.7Z.ai | 1432 | 3,261 | ±10.3 | 33.6 | $1.98 | |
| 65 | R Beam 1.0 501B A23BReflection | 1429 | 1,856 | ±14.2 | 33.8 | $1.00 | |
| 66 | Mistral Large 4Mistral AI | 1428 | 3,975 | ±10.0 | 55.3 | $4.18 | |
| 67 | DeepSeek V3.2DeepSeek | 1428 | 13,730 | ±5.7 | 54.4 | $0.42 | |
| 68 | Claude Haiku 4.5Anthropic | 1427 | 57,374 | ±3.7 | 49.8 | $5.00 | |
| 69 | Gemma 4 26B A4BGoogle | 1427 | 1,712 | ±13.7 | 22.8 | $0.255 | |
| 70 | GLM 4.6Z.ai | 1422 | 9,140 | ±6.5 | 52.2 | $2.20 | |
| 71 | DeepSeek V3.1 TerminusDeepSeek | 1422 | 680 | ±22.2 | Not benchmarked | $1.00 | |
| 72 | Qwen3 VL 235B A22B InstructQwen | 1419 | 2,250 | ±12.8 | Not benchmarked | $1.90 | |
| 73 | Gemini 2.5 FlashGoogle | 1419 | 33,317 | ±3.9 | 28.7 | $2.50 | |
| 74 | MiniMax M2.7MiniMax | 1418 | 36,817 | ±4.5 | 28.4 | $1.20 | |
| 75 | DeepSeek V3.2 ExpDeepSeek | 1418 | 3,061 | ±10.6 | 55.0 | $0.41 | |
| 76 | Grok 4.7xAI | 1416 | 5,586 | ±8.8 | 75.0 | $6.00 | |
| 77 | GPT-6 SolOpenAI | 1416 | 5,776 | ±8.7 | 82.8 | $10.00 | |
| 78 | Mistral Medium 3.5Mistral AI | 1415 | 5,098 | ±9.0 | 9.2 | $7.50 | |
| 79 | Qwen3.5-27BQwen | 1413 | 11,054 | ±6.4 | 22.6 | $2.16 | |
| 80 | GPT-5.2OpenAI | 1413 | 34,079 | ±4.7 | 58.9 | $14.00 | |
| 81 | GLM 4.5Z.ai | 1412 | 5,086 | ±8.5 | 64.2 | $2.20 | |
| 82 | Qwen3.5-122B-A10BQwen | 1410 | 11,736 | ±6.3 | 22.9 | $2.08 | |
| 83 | GPT-6 LunaOpenAI | 1408 | 27,335 | ±5.7 | 71.4 | $0.50 | |
| 84 | GPT-5.4 MiniOpenAI | 1408 | 27,798 | ±5.2 | 28.2 | $4.50 | |
| 85 | Mistral Medium 3.1Mistral AI | 1406 | 27,796 | ±4.2 | Not benchmarked | $2.00 | |
| 86 | Qwen3 Next 80B A3B InstructQwen | 1402 | 5,398 | ±8.2 | Not benchmarked | $1.10 | |
| 87 | T Inkling SmallThinking Machines | 1402 | 16,006 | ±6.1 | 29.9 | $1.20 | |
| 88 | Step 3.5 FlashStepFun | 1402 | 22,820 | ±5.1 | Not benchmarked | $0.30 | |
| 89 | Hy3 previewTencent | 1402 | 3,060 | ±11.3 | 22.4 | $0.60 | |
| 90 | Qwen3 235B A22B Thinking 2507Qwen | 1400 | 1,639 | ±14.2 | Not benchmarked | $3.50 | |
| 91 | GPT-5OpenAI | 1399 | 6,847 | ±7.5 | 72.2 | $10.00 | |
| 92 | Gemini 3.1 Flash Lite PreviewGoogle | 1394 | 27,222 | ±5.2 | 8.1 | $1.50 | |
| 93 | Grok 4.3xAI | 1393 | 33,210 | ±4.9 | 22.5 | $2.50 | |
| 94 | Qwen3.5-FlashQwen | 1392 | 25,667 | ±5.2 | 6.2 | $0.26 | |
| 95 | R1 0528DeepSeek | 1391 | 3,128 | ±10.6 | 71.4 | $2.15 | |
| 96 | Qwen3.5-35B-A3BQwen | 1389 | 11,927 | ±6.2 | 7.7 | $1.00 | |
| 97 | GPT-4.1OpenAI | 1385 | 9,955 | ±6.4 | 46.5 | $8.00 | |
| 98 | Solar Pro 4Upstage | 1382 | 10,670 | ±6.9 | 24.4 | $0.60 | |
| 99 | Qwen3 30B A3B Instruct 2507Qwen | 1378 | 4,942 | ±8.5 | Not benchmarked | $0.30 | |
| 100 | Qwen3 Coder 480B A35BQwen | 1378 | 4,936 | ±8.7 | 50.0 | $1.00 | |
| 101 | o1OpenAI | 1378 | 3,571 | ±9.9 | 61.7 | $60.00 | |
| 102 | o3OpenAI | 1372 | 11,540 | ±6.1 | 70.7 | $8.00 | |
| 103 | GLM 4.5 AirZ.ai | 1366 | 6,775 | ±7.5 | Not benchmarked | $0.85 | |
| 104 | MiniMax M2.5MiniMax | 1366 | 16,260 | ±5.8 | 59.4 | $0.95 | |
| 105 | GPT-5.4 NanoOpenAI | 1365 | 27,714 | ±5.3 | Not benchmarked | $1.25 | |
| 106 | Nemotron 3 SuperNVIDIA | 1362 | 2,270 | ±11.9 | Not benchmarked | $2.40 | |
| 107 | Mistral Medium 3Mistral AI | 1360 | 5,930 | ±8.0 | Not benchmarked | $2.00 | |
| 108 | GLM 4.6VZ.ai | 1357 | 703 | ±22.1 | Not benchmarked | $0.90 | |
| 109 | GPT-5 MiniOpenAI | 1355 | 5,902 | ±8.1 | 59.8 | $2.00 | |
| 110 | Qwen3 Next 80B A3B ThinkingQwen | 1353 | 2,884 | ±10.9 | Not benchmarked | $1.20 | |
| 111 | GLM 4.7 FlashZ.ai | 1345 | 3,377 | ±10.1 | Not benchmarked | $0.40 | |
| 112 | GPT-4.1 MiniOpenAI | 1344 | 7,071 | ±7.5 | 28.5 | $1.60 | |
| 113 | o3 MiniOpenAI | 1343 | 2,160 | ±12.2 | 52.1 | $4.40 | |
| 114 | Nova 2 LiteAmazon | 1335 | 3,072 | ±10.6 | Not benchmarked | $2.50 | |
| 115 | Command ACohere | 1334 | 10,708 | ±6.1 | Not benchmarked | $10.00 | |
| 116 | Gemma 3 27BGoogle | 1333 | 6,675 | ±7.4 | 4.9 | $0.35 | |
| 117 | MiniMax M2MiniMax | 1331 | 1,660 | ±14.4 | 45.3 | $1.02 | |
| 118 | Mercury 2Inception | 1329 | 917 | ±19.3 | 0.0 | $0.75 | |
| 119 | Qwen3 32BQwen | 1327 | 504 | ±24.1 | 40.0 | $0.28 | |
| 120 | MiniMax M1MiniMax | 1326 | 6,985 | ±7.3 | Not benchmarked | $2.20 | |
| 121 | Granite 4.2 8BIBM Granite | 1325 | 1,363 | ±17.1 | Not benchmarked | $0.25 | |
| 122 | Qwen-PlusQwen | 1324 | 690 | ±20.9 | Not benchmarked | $0.78 | |
| 123 | gpt-oss-120bOpenAI | 1319 | 6,566 | ±7.7 | 34.5 | $0.60 | |
| 124 | Trinity Large ThinkingArcee AI | 1318 | 13,083 | ±6.7 | 5.4 | $0.80 | |
| 125 | Gemma 3 12BGoogle | 1317 | 371 | ±27.9 | Not benchmarked | $0.15 | |
| 126 | o4 MiniOpenAI | 1315 | 8,619 | ±6.8 | 68.6 | $4.40 | |
| 127 | GPT-5 NanoOpenAI | 1312 | 1,630 | ±14.4 | 34.8 | $0.40 | |
| 128 | Qwen3 30B A3BQwen | 1312 | 4,497 | ±8.8 | Not benchmarked | $0.50 | |
| 129 | GLM 4.5VZ.ai | 1305 | 1,064 | ±17.8 | Not benchmarked | $1.80 | |
| 130 | Nemotron 3 Nano 30B A3BNVIDIA | 1300 | 4,050 | ±9.6 | Not benchmarked | $0.24 | |
| 131 | Mistral Small 3.1 24BMistral AI | 1299 | 6,341 | ±7.8 | Not benchmarked | $0.555 | |
| 132 | GPT-4o-mini (2024-07-18)OpenAI | 1289 | 8,989 | ±7.0 | 3.6 | $0.60 | |
| 133 | GPT-4o (2024-05-13)OpenAI | 1288 | 14,922 | ±6.9 | Not benchmarked | $15.00 | |
| 134 | GPT-4o (2024-08-06)OpenAI | 1283 | 6,160 | ±8.4 | 23.1 | $10.00 | |
| 135 | GPT-4.1 NanoOpenAI | 1283 | 730 | ±19.9 | 8.9 | $0.40 | |
| 136 | Qwen2.5 72B InstructQwen | 1281 | 6,008 | ±8.1 | Not benchmarked | $0.40 | |
| 137 | Llama 4 MaverickMeta Llama | 1280 | 7,073 | ±7.5 | 18.1 | $0.6525 | |
| 138 | Gemma 3 4BGoogle | 1273 | 444 | ±27.0 | Not benchmarked | $0.05 | |
| 139 | Llama 4 ScoutMeta Llama | 1265 | 5,806 | ±8.3 | 9.1 | $0.30 | |
| 140 | Mistral LargeMistral AI | 1261 | 3,607 | ±9.5 | Not benchmarked | $6.00 | |
| 141 | Llama 3.3 70B InstructMeta Llama | 1255 | 8,327 | ±6.6 | Not benchmarked | $0.32 | |
| 142 | Nova Pro 1.0Amazon | 1255 | 3,398 | ±9.8 | Not benchmarked | $3.20 | |
| 143 | GPT-4 TurboOpenAI | 1254 | 11,559 | ±7.8 | Not benchmarked | $30.00 | |
| 144 | Qwen2.5 Coder 32B InstructQwen | 1251 | 804 | ±18.6 | 30.5 | $1.00 | |
| 145 | gpt-oss-20bOpenAI | 1250 | 2,104 | ±13.3 | Not benchmarked | $0.09 | |
| 146 | Mistral Small 3Mistral AI | 1246 | 1,767 | ±13.5 | Not benchmarked | $0.08 | |
| 147 | Llama 3.1 70B InstructMeta Llama | 1241 | 7,622 | ±7.6 | Not benchmarked | $0.40 | |
| 148 | Nova Lite 1.0Amazon | 1234 | 2,784 | ±10.8 | Not benchmarked | $0.24 | |
| 149 | Gemma 2 27BGoogle | 1230 | 9,918 | ±6.9 | Not benchmarked | $0.65 | |
| 150 | Command R (08-2024)Cohere | 1230 | 1,369 | ±15.2 | Not benchmarked | $0.60 | |
| 151 | Phi 4Microsoft | 1217 | 2,896 | ±10.8 | Not benchmarked | $0.14 | |
| 152 | Nova Micro 1.0Amazon | 1205 | 2,625 | ±11.3 | Not benchmarked | $0.14 | |
| 153 | GPT-4OpenAI | 1190 | 4,251 | ±11.5 | 22.4 | $60.00 | |
| 154 | Llama 3.1 8B InstructMeta Llama | 1181 | 6,736 | ±8.0 | Not benchmarked | $0.08 | |
| 155 | Llama 3.2 3B InstructMeta Llama | 1100 | 1,046 | ±17.8 | Not benchmarked | $0.335 | |
| 156 | Llama 3.2 1B InstructMeta Llama | 1050 | 1,057 | ±18.6 | Not benchmarked | $0.201 |
Only models in our catalog are listed, and each appears once with its best published run. 172 rows were read from the source on October 21, 2026, and rows that match no catalog model are left out. Every other column is a figure the board publishes for the same run.