Skip to content
Last updated: 12m ago
Arena benchmark

LMSYS Chatbot Arena Elo Rating Leaderboard

Human preference rating from 6M+ crowdsourced blind head-to-head comparisons. Users chat with two anonymous models and pick the better response.

Why it matters: The most trusted 'vibes-based' benchmark — reflects real human preferences, not just academic metrics. Widely considered the most meaningful overall ranking.

Top Model

1,507

Claude Fable 5

Average Score

1,377

Across 129 models

Models Tested

129

Metric: Elo rating

Human Baseline

-

Score Range: 9001600

Arena Elo Scores - Top 25 Models

Ranked by Arena Elo score

LMMarketCap.com

Model Rankings

All models with a reported Arena Elo score, ranked by highest Elo rating.

#3
1,497
#4
1,494
#6
1,487
#7
1,486
#8
1,485
#8
1,485
#10
1,481
#11
1,479
#12
1,477
#13
1,476
#14
1,475
#14
1,475
#16
1,474
#17
1,468
#17
1,468
#19
1,467
#20
1,465
#21
1,463
#22
1,462
#23
1,461
#27
1,458
#28
1,457
#29
1,453
#31
1,451
#32
1,449
#33
1,446
#34
1,445
#35
1,444
#36
1,443
#37
1,442
#37
1,442
#37
1,442
#40
1,438
#41
1,434
#42
1,433
#46
1,430
#48
1,425
#48
1,425
#51
1,420
#52
1,418
#53
1,417
#54
1,416
#55
1,415
#58
1,412
#59
1,411
#60
1,408
#62
1,397
#63
1,395
#63
1,395
#66
1,394
#67
1,390
#67
1,390
#69
1,387
#70
1,383
#71
1,380
#71
1,380
#73
1,377
#74
1,373
#75
1,371
#76
1,369
#79
1,368
#80
1,364
#80
1,364
#82
1,354
#84
1,352
#84
1,352
#86
1,350
#87
1,347
#87
1,347
#89
1,346
#91
1,342
#92
1,337
#92
1,337
#94
1,334
#95
1,325
#96
1,322
#97
1,318
#99
1,317
#101
1,306
#102
1,305
#103
1,304
#104
1,300
#105
1,286
#106
1,281
#107
1,280
#108
1,275
#109
1,271
#111
1,262
#112
1,261
#112
1,261
#112
1,261
#112
1,261
#116
1,256
#117
1,255
#119
1,243
#120
1,240
#121
1,232
#122
1,229
#123
1,222
#124
1,211
#125
1,198
#126
1,178
#127
1,166
#128
1,146
#129
1,111

About Arena Elo

Full Name
LMSYS Chatbot Arena Elo Rating
Category
Arena
Metric
Elo rating
Score Range
9001600
Human Baseline
Not established
Status
Active
Frequently Asked Questions

Arena Elo is a standardized evaluation that measures AI model performance on specific tasks. It provides comparable scores across different models, helping developers choose the right model for their needs.

Claude Fable 5 currently holds the top score on the Arena Elo benchmark. See our full rankings table above for the complete leaderboard with 129 models.

We update benchmark data from multiple sources including HuggingFace open-source model leaderboards and LMArena. Scores are refreshed regularly as new evaluations are published and new models are released.

No. While Arena Elo is an important indicator, real-world performance depends on many factors including pricing, latency, context window, and specific task requirements. We recommend using our composite score which weighs multiple benchmarks and practical factors.

Related Benchmarks

Arena Elo Benchmark - AI Model Leaderboard (2026) | LM Market Cap