Updated May 25, 2026

LM Leaderboard — June 2026

Large language models ranked by LMSys Arena Elo, MMLU, HumanEval, MATH, pricing, and inference speed. Refreshed regularly with live data from official provider pricing pages, Artificial Analysis, and the Arena.

What is the top LM on the Arena right now?

LMArena (formerly LMSYS Chatbot Arena) tracks pairwise human votes across hundreds of thousands of conversations. Our June 2026 snapshot below ranks 350 language models on Arena Elo plus the standard MMLU / HumanEval / MATH benchmark suite. The Arena re-ranks roughly weekly as votes accumulate; what you see is the most recent snapshot verified against the public Arena and Artificial Analysis.

350 models
#ModelQualityArena ELOSpeedPriceContextValueReleased
1

OpenAI · Reasoning at any cost

99
151068 t/s$30 / $1801M0.9Apr 2026
2

OpenAI · Frontier general purpose

98
150670 t/s$5 / $301M5.6Apr 2026
3

Anthropic · Coding & agentic workflows

97
150568 t/s$5 / $251M6.5Apr 2026
4

OpenAI · Complex analysis

97
$30 / $1801M0.9Mar 2026
5

OpenAI · Complex analysis

97
$21 / $168400K1.0Dec 2025
6

Anthropic · Complex analysis

97
$30 / $1501M1.1May 2026
7

OpenAI · Deep research

96
$10 / $40200K3.8Oct 2025
8

OpenAI · Deep research

96
$2 / $8200K19.2Oct 2025
9

OpenAI · Hard reasoning

96
$20 / $80200K1.9Jun 2025
10

Google · Speed & cost

96
1505$2 / $121M13.7Feb 2026
11

Google · Speed & cost

96
1505$2 / $121M13.7Feb 2026
12

Anthropic · General purpose

95
1490$5 / $251M6.3Feb 2026
13

Anthropic · General purpose

95
$5 / $25200K6.3Nov 2025
14

Anthropic · Complex analysis

95
$30 / $1501M1.1Apr 2026
15

xAI · Agentic tasks & real-time info

94
149883 t/s$1.25 / $2.51M50.1May 2026
16

Google · Image generation

94
$2 / $1266K13.4Nov 2025
17

Anthropic · Multimodal

94
$15 / $75200K2.1Aug 2025
18

Anthropic · Multimodal

94
$15 / $75200K2.1May 2025
19

Moonshot AI · Frontier quality at low cost

93
146648 t/s$0.73 / $3.49256K44.1Apr 2026
20

OpenAI · General purpose

93
1495$2.5 / $151M10.6Mar 2026
21

OpenAI · General purpose

93
$1.75 / $14128K11.8Mar 2026
22

OpenAI · Code generation

93
$1.75 / $14400K11.8Feb 2026
23

OpenAI · Code generation

93
$1.75 / $14400K11.8Jan 2026
24

OpenAI · General purpose

93
$1.75 / $14128K11.8Dec 2025
25

OpenAI · General purpose

93
$1.75 / $14400K11.8Dec 2025
26

OpenAI · Code generation

93
$1.25 / $10400K16.5Dec 2025
27

OpenAI · General purpose

93
$1.25 / $10400K16.5Nov 2025
28

OpenAI · General purpose

93
$1.25 / $10128K16.5Nov 2025
29

OpenAI · Code generation

93
$1.25 / $10400K16.5Nov 2025
30

OpenAI · Hard reasoning

93
$150 / $600200K0.2Mar 2025
31

OpenAI · Complex analysis

93
$30 / $608K2.1May 2023
32

OpenAI · Multimodal

93
$30 / $608K2.1May 2023
33

xAI · General purpose

93
1496$1.25 / $2.52M49.6Mar 2026
34

OpenAI · Complex analysis

93
$8 / $15272K8.1Apr 2026
35

DeepSeek · Open-source value leader

92
146733 t/s$0.435 / $0.871M141.0Apr 2026
36

OpenAI · Hard reasoning

92
$2 / $8200K18.4Apr 2025
37

· Hard reasoning

91
$0.3 / $1.1164K130.0Jul 2025
38

Google · Speed & cost

91
$1.25 / $101M16.2Jun 2025
39

Google · Speed & cost

91
$1.25 / $101M16.2Jun 2025
40

DeepSeek · Hard reasoning

91
$0.5 / $2.15164K68.7May 2025
41

Google · Speed & cost

91
$1.25 / $101M16.2May 2025
42

DeepSeek · Hard reasoning

91
$0.29 / $0.2933K313.8Jan 2025
43

DeepSeek · Hard reasoning

91
$0.7 / $0.8131K121.3Jan 2025
44

DeepSeek · Hard reasoning

91
$0.7 / $2.564K56.9Jan 2025
45

Anthropic · General purpose

91
1467$3 / $151M10.1Feb 2026
46

· Open-weight agentic & tool use

90
146748 t/s$0.98 / $3.08200K44.3Apr 2026
47

OpenAI · General purpose

90
1455$1.25 / $10400K16.0Aug 2025
48

xAI · General purpose

90
$3 / $15131K10.0Jun 2025
49

xAI · General purpose

90
$3 / $15131K10.0Apr 2025
50

Alibaba Cloud · Open-source

90
$1.04 / $6.24262K24.7Apr 2026
51

Alibaba Cloud · Open-source

90
$2.5 / $7.51M18.0May 2026
52

OpenAI · General purpose

89
$2 / $81M17.8Apr 2025
53

Moonshot AI · Speed & cost

89
1452$0.4 / $1.9262K77.4Jan 2026
54

OpenAI · Multimodal

88
$10 / $10400K8.8Oct 2025
55

OpenAI · Complex analysis

88
$15 / $120400K1.3Oct 2025
56

Anthropic · General purpose

88
$3 / $151M9.8Sep 2025
57

OpenAI · General purpose

88
$2.5 / $10128K14.1Aug 2025
58

OpenAI · Search + citations

88
$2.5 / $10128K14.1Mar 2025
59

OpenAI · Hard reasoning

88
$15 / $60200K2.3Dec 2024
60

OpenAI · General purpose

88
$2.5 / $10128K14.1Nov 2024
61

OpenAI · General purpose

88
$2.5 / $10128K14.1Aug 2024
62

OpenAI · General purpose

88
$2.5 / $10128K14.1May 2024
63

OpenAI · Multimodal

88
$6 / $18128K7.3May 2024
64

OpenAI · General purpose

88
$5 / $15128K8.8May 2024
65

OpenAI · Multimodal

88
$10 / $30128K4.4Apr 2024
66

OpenAI · Complex analysis

88
$10 / $30128K4.4Jan 2024
67

OpenAI · Multimodal

88
$10 / $30128K4.4Nov 2023
68

· Open-source

88
1450$0.6 / $1.9280K69.8Feb 2026
69

DeepSeek · Open-source

87
1455$0.252 / $0.378164K276.2Dec 2025
70

· Open-source

86
$0.135 / $0.5131K270.9Dec 2025
71

DeepSeek · Open-source

86
$0.287 / $0.431164K239.6Dec 2025
72

DeepSeek · Open-source

86
$0.27 / $0.41164K252.9Sep 2025
73

DeepSeek · Open-source

86
$0.27 / $0.95164K141.0Sep 2025
74

DeepSeek · Open-source

86
$0.21 / $0.7933K172.0Aug 2025
75

Anthropic · General purpose

86
$3 / $15200K9.6May 2025
76

DeepSeek · Open-source

86
$0.2 / $0.77164K177.3Mar 2025
77

Anthropic · General purpose

86
$3 / $15200K9.6Feb 2025
78

Anthropic · Hard reasoning

86
$3 / $15200K9.6Feb 2025
79

DeepSeek · Open-source

86
$0.2288 / $0.9144164K150.5Dec 2024
80

DeepSeek · Cheap-and-fast cascade tier

85
1410105 t/s$0.1 / $0.21M566.7Apr 2026
81

Mistral AI · Open-source

85
$0.5 / $1.5262K85.0Dec 2025
82

Mistral AI · Open-source

85
$2 / $6131K21.3Nov 2024
83

Mistral AI · Open-source

85
$2 / $6131K21.3Nov 2024
84

Mistral AI · Open-source

85
$2 / $6128K21.3Feb 2024
85

Cohere · Open-source

84
$2.5 / $10128K13.4Aug 2024
86

Google · Speed & cost

84
$1.5 / $91M16.0May 2026
87

OpenAI · Speed & cost

83
$0.75 / $4.5400K31.6Mar 2026
88

OpenAI · Speed & cost

83
$0.25 / $2400K73.8Aug 2025
89

Alibaba Cloud · Open-source

82
$0.04 / $0.15256K863.2Mar 2026
90

Alibaba Cloud · Open-source

82
$0.139 / $1262K144.0Feb 2026
91

Alibaba Cloud · Open-source

82
$0.195 / $1.56262K93.4Feb 2026
92

Alibaba Cloud · Open-source

82
$0.26 / $2.08262K70.1Feb 2026
93

Alibaba Cloud · Speed & cost

82
$0.065 / $0.261M504.6Feb 2026
94

Alibaba Cloud · Open-source

82
$0.26 / $1.561M90.1Feb 2026
95

Alibaba Cloud · Open-source

82
$0.39 / $2.34262K60.1Feb 2026
96

Alibaba Cloud · Hard reasoning

82
$0.78 / $3.9262K35.0Feb 2026
97

Alibaba Cloud · Code generation

82
$0.11 / $0.8262K180.2Feb 2026
98

Alibaba Cloud · Open-source

82
$0.104 / $0.416131K315.4Oct 2025
99

Alibaba Cloud · Hard reasoning

82
$0.117 / $1.365131K110.7Oct 2025
100

Alibaba Cloud · Open-source

82
$0.08 / $0.5131K282.8Oct 2025
Page 1 of 4 · 1100 of 350
Quality = composite benchmark (MMLU, HumanEval, MATH)Arena ELO = LMSYS Chatbot Arena ratingValue = quality per dollarPrice = input / output per 1M tokens

How the LLM leaderboard works

We pull official provider pricing every 24 hours, Artificial Analysis benchmark snapshots weekly, and LMSys Arena Elo as it publishes. The composite quality index is a 0-100 normalization over MMLU Pro, HumanEval, and MATH, weighted by recency and cross-validated against Arena Elo. We do not accept vendor-supplied numbers without an independent reference.

Where the leaderboard is wrong

No leaderboard predicts your production accuracy. LMSys Arena rewards style and short-conversation polish; a top-Arena model can still under-perform on your specific function-calling schema or long-context retrieval workload. Build an internal eval harness before you commit. See our LMArena Elo explained and LLM routing writeups for the deep-dive.

Related rankings