AI leaderboards

Who's on top right now, ranked by blind head-to-head votes on LMArena. Arrows show moves since the previous published board.

Text ArenaFull board

#ModelLabScoreVotes
1 Gemini 4 Argon (High) google 1526 10,083
2 Claude Opus 5.5 (High) anthropic 1516 10,322
3 Claude Fable 5.1 (Max) anthropic 1513 16,343
4 Claude Opus 5 (Max) anthropic 1508 34,526
5 Claude Opus 5 (High) anthropic 1503 71,020
6 Claude Opus 4.6 (High) anthropic 1501 83,454
7 Muse Wonder (Max) meta 1501 6,001
8 Gemini 3.8 Flash (High) google 1498 43,997
9 Claude Opus 4.6 anthropic 1497 88,206
10 Muse Spark 1.3 (Max) meta 1491 20,506
11 MiMo-V2.6-Pro xiaomi 1491 4,067
12 Claude Fable 5 (High) anthropic 1491 44,253
13 Claude Opus 4.7 (High) anthropic 1490 65,140
14 Gemini 3.7 Flash (High) google 1490 30,501
15 Qwen3.8-Max alibaba 1484 30,500
16 Claude Opus 4.7 anthropic 1483 66,183
17 Muse Spark 1.2 (xHigh) meta 1482 10,470
18 Gemini 3.5 Flash (High) google 1482 48,504
19 Gemini 3.1 Pro Preview google 1480 130,819
20 Gemini 3.6 Flash (High) google 1480 36,102

Board published Oct 22, 2026. Source: LMArena, CC BY 4.0.

WebDev ArenaFull board

#ModelLabScoreVotes
1 Claude Opus 5.5 (Max) anthropic 1807 3,119
2 GPT-6 Astra (Max) openai 1775 6,511
3 Claude Sonnet 5.5 (xHigh) anthropic 1767 3,776
4 GPT-6.1 Sol (Max) openai 1749 3,414
5 Claude Fable 5.1 (Max) anthropic 1743 8,059
6 Muse Wonder Full (Max) meta 1726 2,253
7 Claude Sonnet 5.5 (High) anthropic 1706 5,562
8 Claude Opus 5 (Max) anthropic 1690 18,924
9 GPT-6 Sol (Max) openai 1682 4,961
10 Qwen3.8-Max (0902) alibaba 1673 15,527
11 Gemini 4 Argon (High) google 1673 2,680
12 Qwen3.8-Max alibaba 1673 3,430
13 DeepSeek-V4.1-Flash-20261017 (Max) deepseek 1664 2,425
14 Claude Opus 5 (High) anthropic 1659 25,479
15 Muse Spark 1.3 (Max) meta 1657 9,848
16 Kimi K3 (Max) moonshot 1655 20,258
17 Muse Wonder (Max) meta 1651 2,675
18 Grok 4.7 (xHigh) xai 1637 5,676
19 MiMo-V2.6-Flash xiaomi 1634 5,681
20 Hy4 preview tencent 1631 4,785

Board published Oct 22, 2026. Source: LMArena, CC BY 4.0.

Vision ArenaFull board

#ModelLabScoreVotes
1 Claude Fable 5 (High) anthropic 1325 14,714
2 Claude Opus 5.5 (High) anthropic 1321 3,035
3 Claude Opus 5 (High) anthropic 1320 17,743
4 Claude Fable 5.1 (Max) anthropic 1319 5,026
5 Claude Opus 4.7 anthropic 1317 23,139
6 Claude Opus 4.6 (High) anthropic 1316 22,286
7 Gemini 3.8 Flash (High) google 1315 4,645
8 Gemini 3.7 Flash (High) google 1314 5,369
9 Claude Opus 4.7 (High) anthropic 1313 22,731
10 Qwen3.8-Max alibaba 1313 9,957
11 Claude Opus 4.6 anthropic 1312 26,841
12 Muse Spark 1.3 (Max) meta 1308 5,392
13 Gemini 3.5 Flash (High) google 1308 13,862
14 Gemini 3.5 Flash (Medium) google 1306 14,061
15 Muse Spark meta 1306 5,865
16 Gemini 3 Pro google 1305 13,623
17 Muse Spark 1.2 (xHigh) meta 1304 1,948
18 GPT-5.4 (High) openai 1303 30,747
19 Muse Spark 1.3 (xHigh) meta 1302 4,897
20 Gemini 3.6 Flash (High) google 1299 8,979

Board published Oct 19, 2026. Source: LMArena, CC BY 4.0.

Text to Image ArenaFull board

#ModelLabScoreVotes
1 gpt-image-2.5-sunburst openai 1425 17,752
2 gpt-image-2.5-flare openai 1398 16,889
3 gpt-image-2 (medium) openai 1383 93,334
4 grok-imagine-image-2.0 (canvas) xai 1334 3,113
5 mai-image-2.6 microsoft-ai 1332 25,091
6 gemini-nano-banana-2.1 google 1328 5,310
7 reve-2.1 reve 1302 8,249
8 grok-imagine-image-2.0 (20260801) xai 1294 14,483
9 muse-image meta 1274 42,262
10 reve-2.0 reve 1269 15,773
11 gemini-3.1-flash-image (nano-banana-2) [web-search] google 1262 60,515
12 seedream-5.0-pro bytedance 1255 94,181
13 qwen-image-3.0-pro alibaba 1255 11,440
14 mai-image-2.5 microsoft-ai 1254 61,265
15 gemini-3.1-flash-lite-image (nano-banana-2-lite) google 1250 17,804
16 gemini-3-pro-image-2k (nano-banana-pro) google 1248 175,734
17 gpt-image-1.5-high-fidelity openai 1237 169,927
18 gemini-3-pro-image-preview (nano-banana-pro) google 1234 86,464
19 qwen-image-2.1 alibaba 1223 11,441
20 ideogram-4.0-quality ideogram 1205 60,591

Board published Oct 7, 2026. Source: LMArena, CC BY 4.0.

Questions

What is the top AI model on the LMArena Text leaderboard?

Gemini 4 Argon (High) from google is #1 on the LMArena Text Arena with a score of 1526, on the board published Oct 22, 2026.

What is the top AI model on the LMArena WebDev leaderboard?

Claude Opus 5.5 (Max) from anthropic is #1 on the LMArena WebDev Arena with a score of 1807, on the board published Oct 22, 2026.

What is the top AI model on the LMArena Vision leaderboard?

Claude Fable 5 (High) from anthropic is #1 on the LMArena Vision Arena with a score of 1325, on the board published Oct 19, 2026.

What is the top AI model on the LMArena Text to Image leaderboard?

gpt-image-2.5-sunburst from openai is #1 on the LMArena Text to Image Arena with a score of 1425, on the board published Oct 7, 2026.