LMArena WebDev: HTML leaderboard
- GPT-6.1 Sol leads
- 1800
- models measured
- 100
- lead over #2
- +24 Elo
- median
- 1488
Leader on LMArena WebDev: HTML · read October 21
# LMArena WebDev: HTML, read October 21
leaders = {
"GPT-6.1 Sol": 1800, "GPT-6 Astra": 1775, "Claude Opus 5.5": 1753,
}
On October 21, 2026, 100 of our catalog's models had a LMArena WebDev: HTML result, and OpenAI GPT-6.1 Sol led with 1800.
Web pages built as plain HTML. 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
A coding board we show beside the Vibe Coding Index, not inside it: the index keeps the four boards it was defined on, so a score does not move every time a board is added. Read the methodology
| # | Model | Result | Votes | Interval (±) | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|---|---|
| 1 | GPT-6.1 SolOpenAI | 1800 | 510 | ±32.8 | 88.7 | $10.00 | |
| 2 | GPT-6 AstraOpenAI | 1775 | 1,205 | ±22.1 | 88.7 | $50.00 | |
| 3 | Claude Opus 5.5Anthropic | 1753 | 135 | ±60.8 | 92.2 | $20.00 | |
| 4 | Claude Sonnet 5.5Anthropic | 1741 | 483 | ±34.1 | 88.9 | $10.00 | |
| 5 | Muse WonderMeta | 1694 | 300 | ±36.4 | 64.5 | $20.00 | |
| 6 | DeepSeek V4.1 Flash 1017DeepSeek | 1687 | 295 | ±38.5 | 83.3 | $0.60 | |
| 7 | GPT-6 SolOpenAI | 1685 | 852 | ±23.8 | 82.8 | $10.00 | |
| 8 | Claude Fable 5.1Anthropic | 1684 | 912 | ±23.0 | 89.1 | $50.00 | |
| 9 | Claude Opus 5Anthropic | 1680 | 2,295 | ±14.7 | 81.8 | $25.00 | |
| 10 | Muse Spark 1.3Meta | 1653 | 1,275 | ±18.9 | 79.7 | $4.25 | |
| 11 | Claude Fable 5Anthropic | 1651 | 2,175 | ±14.7 | 82.1 | $50.00 | |
| 12 | Qwen3.8 Max (0902)Qwen | 1649 | 2,529 | ±14.0 | 63.5 | $6.00 | |
| 13 | Kimi K3Moonshot AI | 1644 | 2,678 | ±13.6 | 61.8 | $11.936 | |
| 14 | Gemini 4 ArgonGoogle | 1643 | 185 | ±48.3 | 80.5 | $10.00 | |
| 15 | MiMo-V2.6-FlashXiaomi | 1641 | 812 | ±22.8 | 61.9 | $0.28 | |
| 16 | Grok 4.7xAI | 1627 | 855 | ±22.8 | 75.0 | $6.00 | |
| 17 | Hy4 previewTencent | 1620 | 708 | ±24.6 | 61.6 | $2.501 | |
| 18 | GPT-5.6 SolOpenAI | 1618 | 2,443 | ±13.5 | 76.7 | $20.00 | |
| 19 | Gemini 3.8 FlashGoogle | 1616 | 1,545 | ±17.0 | 70.5 | $4.125 | |
| 20 | MiMo-V2.6-ProXiaomi | 1616 | 722 | ±24.0 | 72.6 | $0.87 | |
| 21 | DeepSeek V4.1 FlashDeepSeek | 1612 | 608 | ±26.2 | 77.2 | $0.525 | |
| 22 | Grok 4.6xAI | 1597 | 1,670 | ±15.9 | 76.4 | $6.00 | |
| 23 | GPT-6 LunaOpenAI | 1595 | 3,220 | ±12.3 | 71.4 | $0.50 | |
| 24 | GLM 5.3Z.ai | 1595 | 1,304 | ±17.9 | 73.1 | $1.40 | |
| 25 | Gemini 3.7 FlashGoogle | 1593 | 1,850 | ±15.4 | 69.9 | $3.75 | |
| 26 | GLM 5.3 FlashZ.ai | 1577 | 2,703 | ±13.1 | 71.0 | $0.50 | |
| 27 | Qwen3.8 27BQwen | 1570 | 2,462 | ±13.3 | 73.6 | $1.35 | |
| 28 | Claude Haiku 5.5Anthropic | 1569 | 449 | ±29.7 | 75.9 | $0.50 | |
| 29 | Grok 4.5xAI | 1567 | 1,599 | ±16.2 | 75.5 | $6.00 | |
| 30 | DeepSeek V4 Pro 0813DeepSeek | 1566 | 548 | ±27.0 | 54.6 | $1.98 | |
| 31 | GLM 5.2Z.ai | 1565 | 2,032 | ±14.6 | 57.7 | $7.00 | |
| 32 | Claude Opus 4.6Anthropic | 1559 | 2,462 | ±13.3 | 66.9 | $25.00 | |
| 33 | DeepSeek V4 Flash 0423DeepSeek | 1558 | 606 | ±25.7 | 54.6 | $0.182 | |
| 34 | Step 5 PreviewStepFun | 1556 | 722 | ±23.8 | 71.4 | $2.70 | |
| 35 | Claude Opus 4.7Anthropic | 1554 | 2,267 | ±13.5 | 51.1 | $25.00 | |
| 36 | Gemini 3.6 FlashGoogle | 1547 | 922 | ±20.9 | 48.3 | $3.75 | |
| 37 | GPT-5.5OpenAI | 1543 | 1,870 | ±15.0 | 67.8 | $30.00 | |
| 38 | Muse Spark 1.2Meta | 1543 | 244 | ±41.6 | 65.1 | $4.25 | |
| 39 | Claude Opus 4.8Anthropic | 1543 | 2,270 | ±13.7 | 66.0 | $25.00 | |
| 40 | Muse Spark 1.1Meta | 1540 | 906 | ±21.4 | 48.9 | $4.25 | |
| 41 | Claude Sonnet 5Anthropic | 1527 | 2,085 | ±14.2 | 63.5 | $10.00 | |
| 42 | Claude Sonnet 4.6Anthropic | 1527 | 2,897 | ±11.9 | 57.8 | $15.00 | |
| 43 | GPT-5.6 TerraOpenAI | 1526 | 1,947 | ±14.7 | 69.0 | $12.00 | |
| 44 | Gemini 3.5 FlashGoogle | 1522 | 1,342 | ±17.1 | 42.8 | $9.00 | |
| 45 | GPT-5.6 LunaOpenAI | 1520 | 1,799 | ±15.4 | 61.5 | $1.20 | |
| 46 | Qwen3.7 MaxQwen | 1512 | 1,044 | ±19.1 | 45.1 | $4.425 | |
| 47 | Claude Opus 4.5Anthropic | 1510 | 6,278 | ±12.6 | 66.8 | $25.00 | |
| 48 | GLM 5.1Z.ai | 1508 | 1,208 | ±18.2 | 44.0 | $4.40 | |
| 49 | Muse Spark OpenMeta | 1495 | 173 | ±48.6 | 62.1 | $4.25 | |
| 50 | Gemini 3.1 Pro PreviewGoogle | 1490 | 2,621 | ±12.2 | 35.3 | $12.00 | |
| 51 | Mistral Large 4Mistral AI | 1487 | 374 | ±35.3 | 55.3 | $4.18 | |
| 52 | Hy3Tencent | 1487 | 970 | ±20.5 | 43.9 | $0.528 | |
| 53 | Kimi K2.6Moonshot AI | 1485 | 1,161 | ±18.2 | 44.2 | $3.41 | |
| 54 | GPT-5.4OpenAI | 1478 | 132 | ±52.9 | 37.7 | $15.00 | |
| 55 | MiMo-V2.5-ProXiaomi | 1473 | 2,896 | ±11.9 | 40.0 | $0.609 | |
| 56 | Qwen3.6 PlusQwen | 1463 | 2,085 | ±13.6 | 37.4 | $1.95 | |
| 57 | MiniMax M3MiniMax | 1455 | 2,689 | ±12.6 | 57.8 | $1.20 | |
| 58 | Kimi K2.7 CodeMoonshot AI | 1451 | 669 | ±24.0 | 39.1 | $3.35 | |
| 59 | GLM 5Z.ai | 1450 | 890 | ±20.7 | 59.7 | $3.20 | |
| 60 | GLM 4.7Z.ai | 1447 | 3,892 | ±13.5 | 33.6 | $1.98 | |
| 61 | R Beam 1.0 501B A23BReflection | 1436 | 405 | ±34.3 | 33.8 | $1.00 | |
| 62 | DeepSeek V4 Pro 0423DeepSeek | 1435 | 1,502 | ±15.9 | 35.3 | $1.9105 | |
| 63 | MiMo-V2.5Xiaomi | 1429 | 1,757 | ±15.0 | 34.0 | $0.238 | |
| 64 | GPT-5.2OpenAI | 1427 | 1,081 | ±23.5 | 58.9 | $14.00 | |
| 65 | GPT-5OpenAI | 1427 | 3,092 | ±16.7 | 72.2 | $10.00 | |
| 66 | Kimi K2.5Moonshot AI | 1426 | 2,585 | ±12.4 | 58.5 | $2.50 | |
| 67 | GPT-5.3-CodexOpenAI | 1422 | 399 | ±31.3 | 29.5 | $14.00 | |
| 68 | GPT-5.4 MiniOpenAI | 1419 | 1,438 | ±16.7 | 28.2 | $4.50 | |
| 69 | MiniMax M2.5MiniMax | 1414 | 965 | ±20.3 | 59.4 | $0.95 | |
| 70 | Qwen3.5 397B A17BQwen | 1410 | 2,604 | ±12.1 | 28.6 | $2.34 | |
| 71 | GPT-5.1OpenAI | 1405 | 4,890 | ±13.0 | 53.3 | $10.00 | |
| 72 | MiniMax M2.7MiniMax | 1401 | 1,976 | ±14.0 | 28.4 | $1.20 | |
| 73 | T InklingThinking Machines | 1399 | 2,174 | ±14.4 | 49.7 | $4.05 | |
| 74 | Claude Sonnet 4.5Anthropic | 1399 | 9,077 | ±11.1 | 59.1 | $15.00 | |
| 75 | Claude Opus 4.1Anthropic | 1399 | 6,911 | ±12.3 | 27.2 | $75.00 | |
| 76 | T Inkling SmallThinking Machines | 1398 | 632 | ±25.7 | 29.9 | $1.20 | |
| 77 | Qwen3.5-27BQwen | 1386 | 934 | ±20.5 | 22.6 | $2.16 | |
| 78 | Gemma 4 31BGoogle | 1380 | 2,025 | ±14.7 | 38.3 | $0.40 | |
| 79 | Solar Pro 4Upstage | 1371 | 813 | ±23.6 | 24.4 | $0.60 | |
| 80 | DeepSeek V3.2DeepSeek | 1371 | 3,269 | ±13.9 | 54.4 | $0.42 | |
| 81 | Grok 4.3xAI | 1367 | 1,769 | ±15.4 | 22.5 | $2.50 | |
| 82 | Gemma 4 26B A4BGoogle | 1362 | 205 | ±43.7 | 22.8 | $0.255 | |
| 83 | GLM 5V TurboZ.ai | 1356 | 247 | ±42.7 | 28.8 | $4.00 | |
| 84 | Hy3 previewTencent | 1356 | 201 | ±44.6 | 22.4 | $0.60 | |
| 85 | Qwen3.5-122B-A10BQwen | 1351 | 988 | ±20.2 | 22.9 | $2.08 | |
| 86 | GLM 4.6Z.ai | 1350 | 6,755 | ±12.3 | 52.2 | $2.20 | |
| 87 | GPT-5.2-CodexOpenAI | 1348 | 2,359 | ±15.2 | 55.1 | $14.00 | |
| 88 | GPT-5.1-CodexOpenAI | 1346 | 4,991 | ±13.0 | 50.5 | $10.00 | |
| 89 | Claude Haiku 4.5Anthropic | 1318 | 10,648 | ±9.3 | 49.8 | $5.00 | |
| 90 | Mistral Medium 3.5Mistral AI | 1308 | 261 | ±41.3 | 9.2 | $7.50 | |
| 91 | MiniMax M2MiniMax | 1306 | 6,685 | ±12.5 | 45.3 | $1.02 | |
| 92 | Qwen3.5-35B-A3BQwen | 1301 | 193 | ±44.8 | 7.7 | $1.00 | |
| 93 | Qwen3.5-FlashQwen | 1291 | 124 | ±59.0 | 6.2 | $0.26 | |
| 94 | Qwen3 Coder 480B A35BQwen | 1287 | 8,578 | ±11.1 | 50.0 | $1.00 | |
| 95 | DeepSeek V3.2 ExpDeepSeek | 1281 | 3,969 | ±14.8 | 55.0 | $0.41 | |
| 96 | Gemini 3.1 Flash Lite PreviewGoogle | 1276 | 1,753 | ±16.4 | 8.1 | $1.50 | |
| 97 | GPT-5.1-Codex-MiniOpenAI | 1253 | 1,154 | ±22.9 | 6.2 | $2.00 | |
| 98 | Trinity Large ThinkingArcee AI | 1240 | 192 | ±49.1 | 5.4 | $0.80 | |
| 99 | Gemini 2.5 ProGoogle | 1235 | 2,730 | ±17.0 | 37.0 | $10.00 | |
| 100 | Mercury 2Inception | 1199 | 108 | ±66.5 | 0.0 | $0.75 |
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.