AI大模型综合能力排行榜

AI大模型综合能力权威排行,基于LMSYS Arena数百万真实人类盲测投票,涵盖Claude、GPT、Gemini、DeepSeek等全球顶尖模型

排名模型机构评分
1Gemma 3 27B ITGoogle
2Amazon Nova Experimental Chat 11 10Amazon
3GLM 4.7 FlashZhipu
4Qwen 3 Next 80B A3B Thinkingalibaba
5Claude 3.7 Sonnet 20250219Anthropic
6Claude 3.5 Sonnet 20241022Anthropic
7trinity-large-thinkingArcee
8GLM 4.5 AirZhipu
9Qwen 2.5 Maxalibaba
10Gemini 2.5 Flash Lite Preview 06 17 ThinkingGoogle

LMSYS Arena 大模型权威排行榜

基于全网数百万真实人类盲测投票的AI大模型能力评测,涵盖代码、数学、创意写作等八大维度

综合性能总榜

排名模型机构变动
🥇
Gemma 3 27B IT
Gemma 3 27B IT
Google
🥈
Amazon Nova Experimental Chat 11 10
Amazon Nova Experimental Chat 11 10
Amazon
🥉
GLM 4.7 Flash
GLM 4.7 Flash
Zhipu
#4
Qwen 3 Next 80B A3B Thinking
Qwen 3 Next 80B A3B Thinking
alibaba
#5
Claude 3.7 Sonnet 20250219
Claude 3.7 Sonnet 20250219
Anthropic
#6
Claude 3.5 Sonnet 20241022
Claude 3.5 Sonnet 20241022
Anthropic
#7
trinity-large-thinking
trinity-large-thinking
Arcee
#8
GLM 4.5 Air
GLM 4.5 Air
Zhipu
#9
Qwen 2.5 Max
Qwen 2.5 Max
alibaba
#10
Gemini 2.5 Flash Lite Preview 06 17 Thinking
Gemini 2.5 Flash Lite Preview 06 17 Thinking
Google
#11
Qwen 3 235B A22B
Qwen 3 235B A22B
alibaba
#12
Trinity Large Preview
Trinity Large Preview
Arcee
#13
GLM 4.6v
GLM 4.6v
Zhipu
#14
Gemini 2.5 Flash Lite Preview 09 2025 No Thinking
Gemini 2.5 Flash Lite Preview 09 2025 No Thinking
Google
#15
Hunyuan Turbos 20250416
Hunyuan Turbos 20250416
Tencent
#16
GPT 4.1 Mini 2025-04-14
GPT 4.1 Mini 2025-04-14
OpenAI
#17
Qwen 3 30B A3B Instruct 2507
Qwen 3 30B A3B Instruct 2507
alibaba
#18
MiniMax M2.1 Preview
MiniMax M2.1 Preview
MiniMax
#19
Mistral Medium 2505
Mistral Medium 2505
Mistral
#20
Claude 3.7 Sonnet 20250219 Thinking 32K
Claude 3.7 Sonnet 20250219 Thinking 32K
Anthropic
#21
Qwen 3 Coder 480B A35B Instruct
Qwen 3 Coder 480B A35B Instruct
alibaba
#22
Mimo V2 Flash (Thinking)
Mimo V2 Flash (Thinking)
Xiaomi
#23
Hunyuan T1 20250711
Hunyuan T1 20250711
Tencent
#24
O1 Preview
O1 Preview
OpenAI
#25
Claude 4 Sonnet 20250514
Claude 4 Sonnet 20250514
Anthropic
#26
O4 Mini 2025-04-16
O4 Mini 2025-04-16
OpenAI
#27
GPT 5 Mini High
GPT 5 Mini High
OpenAI
#28
Mai 1 Preview
Mai 1 Preview
Microsoft
#29
Mimo V2 Flash (Non-Thinking)
Mimo V2 Flash (Non-Thinking)
Xiaomi
#30
minimax-m2-5
minimax-m2-5
minimax
#31
Amazon Nova Experimental Chat 12 10
Amazon Nova Experimental Chat 12 10
Amazon
#32
Step 3.5 Flash
Step 3.5 Flash
StepFun
#33
DeepSeek V3 0324
DeepSeek V3 0324
DeepSeek
#34
Qwen 3 VL 235B A22B Thinking
Qwen 3 VL 235B A22B Thinking
alibaba
#35
Qwen 3.5 Flash
Qwen 3.5 Flash
alibaba
#36
Hunyuan Vision 1.5 Thinking
Hunyuan Vision 1.5 Thinking
Tencent
#37
Qwen 3.5 35B A3B
Qwen 3.5 35B A3B
alibaba
#38
DeepSeek R1
DeepSeek R1
DeepSeek
#39
Claude 4 Sonnet 20250514 Thinking 32K
Claude 4 Sonnet 20250514 Thinking 32K
Anthropic
#40
Qwen 3 235B A22B Thinking 2507
Qwen 3 235B A22B Thinking 2507
alibaba
#41
Longcat Flash Chat
Longcat Flash Chat
MeiTuan
#42
O1 2024-12-17
O1 2024-12-17
OpenAI
#43
Qwen 3 Next 80B A3B Instruct
Qwen 3 Next 80B A3B Instruct
alibaba
#44
Qwen 3 235B A22B No Thinking
Qwen 3 235B A22B No Thinking
alibaba
#45
Grok 4 Fast Reasoning
Grok 4 Fast Reasoning
xAI
#46
Gemini 2.5 Flash Preview 09 2025
Gemini 2.5 Flash Preview 09 2025
Google
#47
GPT 5.4 Nano High
GPT 5.4 Nano High
OpenAI
#48
Qwen 3.5 27B
Qwen 3.5 27B
alibaba
#49
Minimax M2.7
Minimax M2.7
MiniMax
#50
Mistral Medium 2508
Mistral Medium 2508
Mistral
#51
Grok 4 0709
Grok 4 0709
xAI
#52
Claude 4.5 Haiku 20251001
Claude 4.5 Haiku 20251001
Anthropic
#53
Gemini 2.5 Flash
Gemini 2.5 Flash
Google
#54
GLM 4.5
GLM 4.5
Zhipu
#55
Grok 3 Preview 02-24
Grok 3 Preview 02-24
xAI
#56
Claude 4 Opus 20250514
Claude 4 Opus 20250514
Anthropic
#57
GPT 4.1 2025-04-14
GPT 4.1 2025-04-14
OpenAI
#58
Mistral Large 3
Mistral Large 3
Mistral
#59
Qwen 3 VL 235B A22B Instruct
Qwen 3 VL 235B A22B Instruct
alibaba
#60
Amazon Nova Experimental Chat 26-01-10
Amazon Nova Experimental Chat 26-01-10
Amazon
#61
DeepSeek V3.1 Terminus
DeepSeek V3.1 Terminus
DeepSeek
#62
DeepSeek V3.1 Thinking
DeepSeek V3.1 Thinking
DeepSeek
#63
Kimi K2 0711 Preview
Kimi K2 0711 Preview
Moonshot
#64
DeepSeek V3.1 Terminus Thinking
DeepSeek V3.1 Terminus Thinking
DeepSeek
#65
Hunyuan HY3 Preview
Hunyuan HY3 Preview
Tencent
#66
Qwen 3.5 122B A10B
Qwen 3.5 122B A10B
alibaba
#67
DeepSeek V3.1
DeepSeek V3.1
DeepSeek
#68
Kimi K2 0905 Preview
Kimi K2 0905 Preview
Moonshot
#69
Ernie 5.0 Preview 1022
Ernie 5.0 Preview 1022
Baidu
#70
Grok 4 Fast Chat
Grok 4 Fast Chat
xAI
#71
DeepSeek V3.2 Thinking
DeepSeek V3.2 Thinking
DeepSeek
#72
DeepSeek R1 0528
DeepSeek R1 0528
DeepSeek
#73
DeepSeek V3.2 Exp
DeepSeek V3.2 Exp
DeepSeek
#74
Qwen 3 235B A22B Instruct 2507
Qwen 3 235B A22B Instruct 2507
alibaba
#75
DeepSeek V3.2
DeepSeek V3.2
DeepSeek
#76
Claude 4 Opus 20250514 Thinking 16K
Claude 4 Opus 20250514 Thinking 16K
Anthropic
#77
Qwen 3 Max 2025-09-23
Qwen 3 Max 2025-09-23
alibaba
#78
DeepSeek V3.2 Exp Thinking
DeepSeek V3.2 Exp Thinking
DeepSeek
#79
GLM 4.6
GLM 4.6
Zhipu
#80
GPT 5 Chat
GPT 5 Chat
OpenAI
#81
Amazon Nova Experimental Chat 26-02-10
Amazon Nova Experimental Chat 26-02-10
Amazon
#82
MiMo V2.5
MiMo V2.5
xiaomi
#83
Kimi K2 Thinking Turbo
Kimi K2 Thinking Turbo
Moonshot
#84
O3 2025-04-16
O3 2025-04-16
OpenAI
#85
Grok 4.1 Fast Reasoning
Grok 4.1 Fast Reasoning
xAI
#86
Kimi K2.5 Instant
Kimi K2.5 Instant
Moonshot
#87
DeepSeek V4 Flash
DeepSeek V4 Flash
DeepSeek
#88
GPT 5 High
GPT 5 High
OpenAI
#89
Qwen 3 Max Preview
Qwen 3 Max Preview
alibaba
#90
Longcat Flash Chat 2602 Exp
Longcat Flash Chat 2602 Exp
MeiTuan
#91
GPT 5.2 Chat
GPT 5.2 Chat
OpenAI
#92
Gemini 3.1 Flash Lite Preview
Gemini 3.1 Flash Lite Preview
Google
#93
Gemma 4 26B A4B
Gemma 4 26B A4B
Google
#94
GPT 5.1
GPT 5.1
OpenAI
#95
GPT 5.2 High
GPT 5.2 High
OpenAI
#96
DeepSeek V4 Flash Thinking
DeepSeek V4 Flash Thinking
DeepSeek
#97
GLM 4.7
GLM 4.7
Zhipu
#98
ChatGPT 4o Latest 20250326
ChatGPT 4o Latest 20250326
OpenAI
#99
Qwen 3.6 Plus
Qwen 3.6 Plus
alibaba
#100
GPT 4.5 Preview 2025-02-27
GPT 4.5 Preview 2025-02-27
OpenAI
#101
Qwen 3.5 397B A17B
Qwen 3.5 397B A17B
alibaba
#102
Gemini 2.5 Pro
Gemini 2.5 Pro
Google
#103
Claude 4.1 Opus 20250805
Claude 4.1 Opus 20250805
Anthropic
#104
MiMo V2 Pro
MiMo V2 Pro
Xiaomi
#105
Claude 4.1 Opus 20250805 Thinking 16K
Claude 4.1 Opus 20250805 Thinking 16K
Anthropic
#106
GPT 5.3 Chat Latest
GPT 5.3 Chat Latest
OpenAI
#107
Ernie 5.0 Preview 1203
Ernie 5.0 Preview 1203
Baidu
#108
Kimi K2.5 Thinking
Kimi K2.5 Thinking
Moonshot
#109
Ernie 5.0 0110
Ernie 5.0 0110
Baidu
#110
Grok 4.3
Grok 4.3
xAI
#111
Gemma 4 31B
Gemma 4 31B
Google
#112
GPT 5.4 Mini High
GPT 5.4 Mini High
OpenAI
#113
Claude 4.5 Sonnet 20250929
Claude 4.5 Sonnet 20250929
Anthropic
#114
Claude 4.5 Sonnet 20250929 Thinking 32K
Claude 4.5 Sonnet 20250929 Thinking 32K
Anthropic
#115
GPT 5.1 High
GPT 5.1 High
OpenAI
#116
Dola Seed 2.0 Pro
Dola Seed 2.0 Pro
ByteDance
#117
GLM 5
GLM 5
Zhipu
#118
Qwen 3.6 Max Preview
Qwen 3.6 Max Preview
alibaba
#119
DeepSeek V4 Pro
DeepSeek V4 Pro
DeepSeek
#120
Grok 4.1
Grok 4.1
xAI
#121
DeepSeek V4 Pro Thinking
DeepSeek V4 Pro Thinking
DeepSeek
#122
Kimi K2.6
Kimi K2.6
moonshot
#123
Gemini 3 Flash (Thinking Minimal)
Gemini 3 Flash (Thinking Minimal)
Google
#124
Qwen 3.5 Max Preview
Qwen 3.5 Max Preview
alibaba
#125
MiMo V2.5 Pro
MiMo V2.5 Pro
Xiaomi
#126
Grok 4.1 Thinking
Grok 4.1 Thinking
xAI
#127
GPT 5.4
GPT 5.4
OpenAI
#128
Claude 4.5 Opus 20251101
Claude 4.5 Opus 20251101
Anthropic
#129
Claude 4.6 Sonnet
Claude 4.6 Sonnet
Anthropic
#130
GPT 5.5 Instant
GPT 5.5 Instant
OpenAI
#131
GLM 5.1
GLM 5.1
Zhipu
#132
Claude 4.5 Opus 20251101 Thinking 32K
Claude 4.5 Opus 20251101 Thinking 32K
Anthropic
#133
Ernie 5.1
Ernie 5.1
Baidu
#134
Gemini 3 Flash
Gemini 3 Flash
Google
#135
Grok 4.20 Beta Multi Agent
Grok 4.20 Beta Multi Agent
xAI
#136
Grok 4.20 Beta Reasoning
Grok 4.20 Beta Reasoning
xAI
#137
Qwen 3.7 Max Preview
Qwen 3.7 Max Preview
alibaba
#138
GPT 5.2 Chat 0210
GPT 5.2 Chat 0210
OpenAI
#139
Grok 4.20 Beta
Grok 4.20 Beta
xAI
#140
GPT 5.5
GPT 5.5
OpenAI
#141
GPT 5.4 High
GPT 5.4 High
OpenAI
#142
Gemini 3.5 Flash
Gemini 3.5 Flash
Google
#143
GPT 5.5 High
GPT 5.5 High
OpenAI
#144
Gemini 3 Pro
Gemini 3 Pro
Google
#145
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview
Google
#146
Muse Spark
Muse Spark
Meta
#147
Claude 4.7 Opus
Claude 4.7 Opus
Anthropic
#148
Claude 4.6 Opus
Claude 4.6 Opus
Anthropic
#149
Claude 4.7 Opus Thinking
Claude 4.7 Opus Thinking
Anthropic
#150
Claude 4.6 Opus Thinking
Claude 4.6 Opus Thinking
Anthropic