LMArena Text: Polish leaderboard
- models measured
- 121
- lead over #2
- +3 Elo
- median
- 1423
Leader on LMArena Text: Polish · read October 21
On October 21, 2026, 121 of our catalog's models had a LMArena Text: Polish result, and Anthropic Claude Fable 5.1 led with 1525.
Prompts written in Polish. 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 | Claude Fable 5.1Anthropic | 1525 | 240 | ±37.0 | 89.1 | $50.00 | |
| 2 | Claude Opus 5Anthropic | 1522 | 526 | ±25.2 | 81.8 | $25.00 | |
| 3 | Gemini 3.5 FlashGoogle | 1516 | 797 | ±21.4 | 42.8 | $9.00 | |
| 4 | Gemini 3.7 FlashGoogle | 1503 | 453 | ±27.7 | 69.9 | $3.75 | |
| 5 | Muse Spark 1.1Meta | 1499 | 671 | ±23.1 | 48.9 | $4.25 | |
| 6 | Claude Opus 4.6Anthropic | 1499 | 1,561 | ±15.2 | 66.9 | $25.00 | |
| 7 | Gemini 3.1 Pro PreviewGoogle | 1498 | 2,473 | ±12.3 | 35.3 | $12.00 | |
| 8 | Gemini 3.8 FlashGoogle | 1497 | 596 | ±24.3 | 70.5 | $4.125 | |
| 9 | Claude Fable 5Anthropic | 1494 | 646 | ±22.7 | 82.1 | $50.00 | |
| 10 | Muse Spark 1.3Meta | 1490 | 281 | ±35.2 | 79.7 | $4.25 | |
| 11 | Claude Opus 4.7Anthropic | 1489 | 1,122 | ±17.8 | 51.1 | $25.00 | |
| 12 | Gemini 2.5 ProGoogle | 1479 | 6,495 | ±8.4 | 37.0 | $10.00 | |
| 13 | Gemini 3.6 FlashGoogle | 1473 | 529 | ±25.4 | 48.3 | $3.75 | |
| 14 | GPT-5.4OpenAI | 1472 | 1,317 | ±16.6 | 37.7 | $15.00 | |
| 15 | Qwen3.8 Max (0902)Qwen | 1471 | 432 | ±27.2 | 63.5 | $6.00 | |
| 16 | GLM 5.3Z.ai | 1466 | 350 | ±30.9 | 73.1 | $1.40 | |
| 17 | GPT-5.5OpenAI | 1465 | 1,168 | ±17.5 | 67.8 | $30.00 | |
| 18 | MiMo-V2.5-ProXiaomi | 1464 | 1,376 | ±16.2 | 40.0 | $0.609 | |
| 19 | DeepSeek V4 Pro 0423DeepSeek | 1461 | 1,125 | ±17.9 | 35.3 | $1.9105 | |
| 20 | Claude Opus 4.8Anthropic | 1459 | 1,091 | ±17.6 | 66.0 | $25.00 | |
| 21 | GPT-5.6 SolOpenAI | 1459 | 631 | ±23.4 | 76.7 | $20.00 | |
| 22 | Kimi K3Moonshot AI | 1458 | 574 | ±24.0 | 61.8 | $11.936 | |
| 23 | DeepSeek V4.1 FlashDeepSeek | 1457 | 222 | ±37.1 | 77.2 | $0.525 | |
| 24 | GLM 5.2Z.ai | 1456 | 834 | ±20.6 | 57.7 | $7.00 | |
| 25 | MiMo-V2.6-FlashXiaomi | 1455 | 200 | ±41.1 | 61.9 | $0.28 | |
| 26 | T InklingThinking Machines | 1450 | 625 | ±23.5 | 49.7 | $4.05 | |
| 27 | GLM 5.3 FlashZ.ai | 1450 | 610 | ±23.4 | 71.0 | $0.50 | |
| 28 | GLM 5.1Z.ai | 1449 | 1,178 | ±17.1 | 44.0 | $4.40 | |
| 29 | Qwen3.7 PlusQwen | 1449 | 807 | ±20.4 | Not benchmarked | $1.28 | |
| 30 | Qwen3.5 397B A17BQwen | 1447 | 1,687 | ±14.4 | 28.6 | $2.34 | |
| 31 | GLM 4.6Z.ai | 1447 | 1,301 | ±16.2 | 52.2 | $2.20 | |
| 32 | Hy3Tencent | 1447 | 241 | ±36.6 | 43.9 | $0.528 | |
| 33 | GPT-5.6 TerraOpenAI | 1446 | 654 | ±22.6 | 69.0 | $12.00 | |
| 34 | Kimi K2.5Moonshot AI | 1445 | 1,521 | ±14.8 | 58.5 | $2.50 | |
| 35 | Gemini 3.1 Flash Lite PreviewGoogle | 1443 | 1,266 | ±16.5 | 8.1 | $1.50 | |
| 36 | Claude Sonnet 4.6Anthropic | 1443 | 1,407 | ±15.8 | 57.8 | $15.00 | |
| 37 | GPT-5.1OpenAI | 1440 | 1,323 | ±15.8 | 53.3 | $10.00 | |
| 38 | Qwen3.8 27BQwen | 1439 | 389 | ±29.6 | 73.6 | $1.35 | |
| 39 | Claude Opus 4.5Anthropic | 1439 | 1,892 | ±13.6 | 66.8 | $25.00 | |
| 40 | o3OpenAI | 1438 | 3,835 | ±10.7 | 70.7 | $8.00 | |
| 41 | Kimi K2.6Moonshot AI | 1438 | 759 | ±20.8 | 44.2 | $3.41 | |
| 42 | Gemini 3.5 Flash LiteGoogle | 1437 | 522 | ±25.5 | 33.6 | $2.50 | |
| 43 | DeepSeek V4 Flash 0423DeepSeek | 1436 | 1,026 | ±18.6 | 54.6 | $0.182 | |
| 44 | GLM 4.7Z.ai | 1435 | 461 | ±25.6 | 33.6 | $1.98 | |
| 45 | DeepSeek V3.2 ExpDeepSeek | 1435 | 397 | ±28.9 | 55.0 | $0.41 | |
| 46 | GLM 5Z.ai | 1434 | 604 | ±23.2 | 59.7 | $3.20 | |
| 47 | Gemma 4 31BGoogle | 1433 | 202 | ±37.5 | 38.3 | $0.40 | |
| 48 | Qwen3.6 PlusQwen | 1433 | 995 | ±18.6 | 37.4 | $1.95 | |
| 49 | GLM 5V TurboZ.ai | 1432 | 196 | ±41.4 | 28.8 | $4.00 | |
| 50 | Grok 4.5xAI | 1432 | 626 | ±23.6 | 75.5 | $6.00 | |
| 51 | GPT-5OpenAI | 1431 | 1,796 | ±14.6 | 72.2 | $10.00 | |
| 52 | Grok 4.6xAI | 1430 | 465 | ±26.8 | 76.4 | $6.00 | |
| 53 | Mistral Medium 3.1Mistral AI | 1430 | 3,327 | ±10.5 | Not benchmarked | $2.00 | |
| 54 | Mistral Medium 3.5Mistral AI | 1430 | 233 | ±37.1 | 9.2 | $7.50 | |
| 55 | R1 0528DeepSeek | 1428 | 1,980 | ±14.2 | 71.4 | $2.15 | |
| 56 | T Inkling SmallThinking Machines | 1428 | 483 | ±27.2 | 29.9 | $1.20 | |
| 57 | DeepSeek V3.1 TerminusDeepSeek | 1427 | 205 | ±38.8 | Not benchmarked | $1.00 | |
| 58 | GPT-5.2OpenAI | 1426 | 1,633 | ±14.9 | 58.9 | $14.00 | |
| 59 | Claude Sonnet 5Anthropic | 1425 | 732 | ±21.9 | 63.5 | $10.00 | |
| 60 | MiniMax M3MiniMax | 1423 | 1,138 | ±17.6 | 57.8 | $1.20 | |
| 61 | Claude Sonnet 4.5Anthropic | 1423 | 2,223 | ±12.7 | 59.1 | $15.00 | |
| 62 | GLM 4.5Z.ai | 1422 | 1,675 | ±14.8 | 64.2 | $2.20 | |
| 63 | GPT-6 AstraOpenAI | 1422 | 184 | ±42.1 | 88.7 | $50.00 | |
| 64 | Grok 4.7xAI | 1420 | 187 | ±41.1 | 75.0 | $6.00 | |
| 65 | Qwen3 VL 235B A22B InstructQwen | 1419 | 540 | ±26.5 | Not benchmarked | $1.90 | |
| 66 | DeepSeek V3.2DeepSeek | 1419 | 1,119 | ±17.1 | 54.4 | $0.42 | |
| 67 | GPT-5.4 MiniOpenAI | 1415 | 1,189 | ±17.4 | 28.2 | $4.50 | |
| 68 | Gemini 2.5 FlashGoogle | 1413 | 6,188 | ±8.3 | 28.7 | $2.50 | |
| 69 | Claude Opus 4.1Anthropic | 1413 | 3,734 | ±10.2 | 27.2 | $75.00 | |
| 70 | MiMo-V2.5Xiaomi | 1413 | 945 | ±18.9 | 34.0 | $0.238 | |
| 71 | GPT-5.6 LunaOpenAI | 1405 | 611 | ±23.9 | 61.5 | $1.20 | |
| 72 | Qwen3.5-122B-A10BQwen | 1398 | 601 | ±23.4 | 22.9 | $2.08 | |
| 73 | Grok 4.3xAI | 1398 | 1,200 | ±17.5 | 22.5 | $2.50 | |
| 74 | Qwen3 Next 80B A3B InstructQwen | 1398 | 1,023 | ±18.5 | Not benchmarked | $1.10 | |
| 75 | Qwen3 235B A22B Thinking 2507Qwen | 1390 | 783 | ±20.6 | Not benchmarked | $3.50 | |
| 76 | Step 3.5 FlashStepFun | 1389 | 1,365 | ±16.2 | Not benchmarked | $0.30 | |
| 77 | GPT-4.1OpenAI | 1389 | 3,049 | ±11.5 | 46.5 | $8.00 | |
| 78 | MiniMax M2.7MiniMax | 1387 | 1,680 | ±14.8 | 28.4 | $1.20 | |
| 79 | Nemotron 3 UltraNVIDIA | 1385 | 228 | ±37.7 | Not benchmarked | $2.40 | |
| 80 | Qwen3.5-35B-A3BQwen | 1385 | 587 | ±23.0 | 7.7 | $1.00 | |
| 81 | GPT-6 LunaOpenAI | 1383 | 883 | ±20.7 | 71.4 | $0.50 | |
| 82 | GPT-5 MiniOpenAI | 1378 | 1,562 | ±15.5 | 59.8 | $2.00 | |
| 83 | Qwen3.5-FlashQwen | 1376 | 1,286 | ±16.4 | 6.2 | $0.26 | |
| 84 | Qwen3.5-27BQwen | 1375 | 537 | ±24.8 | 22.6 | $2.16 | |
| 85 | GPT-6 SolOpenAI | 1372 | 196 | ±41.9 | 82.8 | $10.00 | |
| 86 | Mistral Medium 3Mistral AI | 1371 | 2,887 | ±11.7 | Not benchmarked | $2.00 | |
| 87 | GLM 4.5 AirZ.ai | 1368 | 1,863 | ±14.2 | Not benchmarked | $0.85 | |
| 88 | GPT-5.4 NanoOpenAI | 1366 | 1,129 | ±18.2 | Not benchmarked | $1.25 | |
| 89 | GPT-4o (2024-05-13)OpenAI | 1365 | 166 | ±56.8 | Not benchmarked | $15.00 | |
| 90 | o4 MiniOpenAI | 1358 | 2,795 | ±11.8 | 68.6 | $4.40 | |
| 91 | gpt-oss-120bOpenAI | 1353 | 1,732 | ±14.5 | 34.5 | $0.60 | |
| 92 | Qwen3 30B A3B Instruct 2507Qwen | 1353 | 1,541 | ±15.2 | Not benchmarked | $0.30 | |
| 93 | Nemotron 3 SuperNVIDIA | 1346 | 276 | ±34.8 | Not benchmarked | $2.40 | |
| 94 | Gemma 3 27BGoogle | 1345 | 2,829 | ±11.7 | 4.9 | $0.35 | |
| 95 | Qwen3 Next 80B A3B ThinkingQwen | 1345 | 709 | ±22.2 | Not benchmarked | $1.20 | |
| 96 | Qwen3 Coder 480B A35BQwen | 1344 | 1,618 | ±15.1 | 50.0 | $1.00 | |
| 97 | Claude Haiku 4.5Anthropic | 1343 | 3,508 | ±10.6 | 49.8 | $5.00 | |
| 98 | MiniMax M2.5MiniMax | 1334 | 928 | ±19.3 | 59.4 | $0.95 | |
| 99 | MiniMax M1MiniMax | 1329 | 3,528 | ±10.7 | Not benchmarked | $2.20 | |
| 100 | Nova 2 LiteAmazon | 1327 | 421 | ±29.6 | Not benchmarked | $2.50 | |
| 101 | GPT-4.1 MiniOpenAI | 1326 | 2,665 | ±12.2 | 28.5 | $1.60 | |
| 102 | Command ACohere | 1324 | 3,071 | ±11.3 | Not benchmarked | $10.00 | |
| 103 | GPT-5 NanoOpenAI | 1314 | 571 | ±25.0 | 34.8 | $0.40 | |
| 104 | Trinity Large ThinkingArcee AI | 1312 | 568 | ±26.4 | 5.4 | $0.80 | |
| 105 | MiniMax M2MiniMax | 1312 | 280 | ±35.8 | 45.3 | $1.02 | |
| 106 | Solar Pro 4Upstage | 1304 | 330 | ±34.1 | 24.4 | $0.60 | |
| 107 | Nemotron 3 Nano 30B A3BNVIDIA | 1303 | 532 | ±26.4 | Not benchmarked | $0.24 | |
| 108 | GLM 4.5VZ.ai | 1302 | 281 | ±34.1 | Not benchmarked | $1.80 | |
| 109 | GPT-4 TurboOpenAI | 1302 | 178 | ±56.4 | Not benchmarked | $30.00 | |
| 110 | Qwen3 30B A3BQwen | 1299 | 2,005 | ±13.7 | Not benchmarked | $0.50 | |
| 111 | o3 MiniOpenAI | 1294 | 2,639 | ±12.3 | 52.1 | $4.40 | |
| 112 | GLM 4.7 FlashZ.ai | 1291 | 318 | ±32.9 | Not benchmarked | $0.40 | |
| 113 | Gemma 2 27BGoogle | 1277 | 58 | ±73.2 | Not benchmarked | $0.65 | |
| 114 | Llama 4 MaverickMeta Llama | 1275 | 2,675 | ±12.5 | 18.1 | $0.6525 | |
| 115 | GPT-4OpenAI | 1265 | 119 | ±63.9 | 22.4 | $60.00 | |
| 116 | Llama 4 ScoutMeta Llama | 1265 | 2,469 | ±13.0 | 9.1 | $0.30 | |
| 117 | Llama 3.3 70B InstructMeta Llama | 1259 | 1,453 | ±16.8 | Not benchmarked | $0.32 | |
| 118 | gpt-oss-20bOpenAI | 1252 | 809 | ±22.0 | Not benchmarked | $0.09 | |
| 119 | GPT-4o-mini (2024-07-18)OpenAI | 1244 | 65 | ±65.7 | 3.6 | $0.60 | |
| 120 | Mistral Small 3.1 24BMistral AI | 1242 | 2,793 | ±12.4 | Not benchmarked | $0.555 | |
| 121 | Mistral LargeMistral AI | 1157 | 170 | ±57.6 | Not benchmarked | $6.00 |
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.