连接 AI · 赋能个体 · 探索前沿 AI 工具与模型
English

一站式发现最新 AI 模型排名、实用工具推荐与深度文章 —— 让 AI 为你所用。

# 模型 机构 得分 详情
🥇
o1-preview-2024-09-12
OpenAI
livebench
OpenAI
100.0
🚀 2024-09-12
🥈
sonar-pro
Perplexity
livebench
Perplexity
88.6
💰 $3.0/$15.0 📝 8000 📏 200000 🚀 2025-01-21
🥉
gemini-2.5-pro-exp-03-25
Google
livebench
Google
85.0
🚀 2025-03-25
4
o1-2024-12-17-medium
OpenAI
livebench
OpenAI
83.4
🚀 2024-12-17
5
o1-2024-12-17-high
OpenAI
livebench
OpenAI
81.8
🚀 2024-12-17
6
claude-3-7-sonnet-20250219-thinking-64k
Anthropic
livebench
Anthropic
81.0
—
7
gpt-4.5-preview-2025-02-27
OpenAI
livebench
OpenAI
79.8
🚀 2025-02-27
8
claude-3-7-sonnet-20250219-thinking-25k
Anthropic
livebench
Anthropic
79.0
—
9
o1-2024-12-17-low
OpenAI
livebench
OpenAI
78.6
🚀 2024-12-17
10
claude-3-7-sonnet-20250219-base
Anthropic
livebench
Anthropic
78.3
—
11
claude-3-5-sonnet-20241022
Anthropic
livebench
Anthropic
72.3
—
12
grok-3-beta
xAI
livebench
xAI
71.8
💰 $3.0/$15.0 📏 131072 🚀 2025-02-17
13
claude-3-opus-20240229
Anthropic
livebench
Anthropic
67.6
🚀 2024-03-04
14
claude-3-5-sonnet-20240620
Anthropic
livebench
Anthropic
66.8
—
15
gemini-2.0-flash
Google
livebench
Google
66.7
🚀 2025-02-05
16
grok-3
xAI
livebench
xAI
65.9
💰 $3.0/$15.0 📏 131072 🚀 2025-02-17
17
chatgpt-4o-latest-2025-03-27
OpenAI
livebench
OpenAI
65.8
🚀 2024-08-08
18
deepseek-r1-local-2
DeepSeek
livebench
DeepSeek
64.5
🚀 2025-01-20
19
Meta-Llama-3.1-405B-Instruct-Turbo
Meta
livebench
Meta
64.0
—
20
o3-mini-2025-01-31-high
OpenAI
livebench
OpenAI
63.3
🚀 2025-01-31
21
chatgpt-4o-latest-2025-01-29
OpenAI
livebench
OpenAI
63.2
🚀 2024-08-08
22
gpt-4o-2024-11-20
OpenAI
livebench
OpenAI
62.7
💰 $2.5/$10.0 📝 16384 📏 128000 🚀 2024-11-20
23
grok-2-1212
xAI
livebench
xAI
61.8
🚀 2024-08-13
24
chatgpt-4o-latest-2025-01-30
OpenAI
livebench
OpenAI
61.7
🚀 2024-08-08
25
hunyuan-turbos-20250313
Tencent
livebench
Tencent
61.0
—
26
grok-beta
xAI
livebench
xAI
60.0
—
27
deepseek-r1-local
DeepSeek
livebench
DeepSeek
59.4
🚀 2025-01-20
28
o1-mini-2024-09-12
OpenAI
livebench
OpenAI
58.6
🚀 2024-09-12
29
o3-mini-2025-01-31-medium
OpenAI
livebench
OpenAI
57.4
🚀 2025-01-31
30
step-2-16k-202411
StepFun
livebench
StepFun
56.4
🚀 2024-09-24
31
sonar
Perplexity
livebench
Perplexity
55.3
💰 $1.0/$1.0 📏 127072 🚀 2025-01-21
32
dracarys2-llama-3.1-70b-instruct
Meta
livebench
Meta
54.4
—
33
llama-3.3-70b-instruct-turbo
Meta
livebench
Meta
54.3
—
34
Meta-Llama-3.1-70B-Instruct-Turbo
Meta
livebench
Meta
54.2
—
35
coding-meta-llama-3.1-70b-instruct-chk-50
Meta
livebench
Meta
53.2
—
36
coding2-amcfull-apifull-mmlu12k-meta-llama-3.1-70b-instruct-chk-150
Meta
livebench
Meta
52.9
—
37
learnlm-1.5-pro-experimental
Unknown
livebench
Unknown
52.3
—
38
amazon.nova-pro-v1:0
Amazon
livebench
Amazon
52.2
—
39
claude-3-5-haiku-20241022
Anthropic
livebench
Anthropic
50.1
—
40
o3-mini-2025-01-31-low
OpenAI
livebench
OpenAI
50.1
🚀 2025-01-31
41
grok-2-mini
xAI
livebench
xAI
50.0
🚀 2024-08-13
42
claude-3-sonnet-20240229
Anthropic
livebench
Anthropic
48.7
🚀 2024-03-04
43
gemini-2.0-flash-lite-preview-02-05
Google
livebench
Google
48.3
🚀 2025-02-05
44
grok-3-mini-reasoning-beta
xAI
livebench
xAI
47.5
🚀 2025-02-17
45
codegen3_5k-qwen2.5-72b-instruct-2-chk-50
Alibaba
code livebench
Alibaba
47.3
—
46
command-a-03-2025
Cohere
livebench
Cohere
46.5
🚀 2025-03-13
47
gemini-2.0-flash-lite-001
Google
livebench
Google
45.0
💰 $0.07/$0.3 📝 8192 📏 1048576 🚀 2025-02-05
48
Qwen2.5-72B-Instruct-Turbo
Alibaba
livebench
Alibaba
44.6
—
49
mistral-small-2501
Mistral AI
livebench
Mistral AI
44.4
—
50
grok-2
xAI
livebench
xAI
44.2
🚀 2024-08-13
51
Meta-Llama-3-70B-Instruct
Meta
Open livebench
Meta
43.3
📐 70.554B 🚀 2024-04-17
52
Reflection-Llama-3.1-70B
Meta
Open livebench
Meta
42.8
📐 69.5B
53
mistral-small-2503
Mistral AI
livebench
Mistral AI
42.6
—
54
deepseek-coder
DeepSeek
code livebench
DeepSeek
41.8
—
55
wbot-4:347b_no_s
Unknown
livebench
Unknown
41.0
—
56
command-r-plus-08-2024
Cohere
livebench
Cohere
39.1
💰 $2.5/$10.0 📝 4000 📏 128000 🚀 2024-04-04
57
lcb-math-qwen2-72b-instructv3-merged-50
Alibaba
livebench
Alibaba
39.0
—
58
deepseek-chat
DeepSeek
livebench
DeepSeek
37.9
💰 $0.32/$0.89 📝 163840 📏 163840
59
acm_rewrite_qwen2-72B-Chat
Alibaba
livebench
Alibaba
37.7
—
60
Qwen2-72B-Instruct
Alibaba
Open livebench
Alibaba
36.2
📐 72.706B 🚀 2024-05-28
61
amazon.nova-lite-v1:0
Amazon
livebench
Amazon
35.9
—
62
azerogpt
Unknown
livebench
Unknown
35.1
—
63
mistral-small-2409
Mistral AI
livebench
Mistral AI
34.7
🚀 2024-09-17
64
Dracarys2-72B-Instruct
Unknown
livebench
Unknown
34.6
—
65
DeepSeek-R1-Distill-Qwen-32B
DeepSeek
Open livebench
DeepSeek
33.6
📐 32.764B 🚀 2025-01-20
66
claude-3-haiku-20240307
Anthropic
livebench
Anthropic
33.2
🚀 2024-03-13
67
Llama-3.1-Nemotron-70B-Instruct-HF
NVIDIA
Open livebench
NVIDIA
31.9
📐 70.554B 🚀 2024-10-12
68
open-mixtral-8x22b
Mistral AI
livebench
Mistral AI
30.5
—
69
Qwen2.5-Coder-32B-Instruct
Alibaba
Open code livebench
Alibaba
30.5
📐 32.764B 🚀 2024-11-06
70
QwQ-32B-Preview
Alibaba
Open livebench
Alibaba
29.2
📐 32.764B 🚀 2024-11-27
71
command-r-08-2024
Cohere
livebench
Cohere
27.9
💰 $0.15/$0.6 📝 4000 📏 128000 🚀 2024-03-11
72
amazon.nova-micro-v1:0
Amazon
livebench
Amazon
27.1
—
73
sky-t1-32b-preview
Unknown
livebench
Unknown
25.1
—
74
Meta-Llama-3.1-8B-Instruct-Turbo
Meta
livebench
Meta
24.8
—
75
command-r-plus-04-2024
Cohere
livebench
Cohere
24.6
🚀 2024-04-04
76
mistral-small-2402
Mistral AI
livebench
Mistral AI
23.4
—
77
Meta-Llama-3-8B-Instruct
Meta
Open livebench
Meta
23.1
📐 8.03B 🚀 2024-04-17
78
gemini-1.5-flash-8b-exp-0924
Google
livebench
Google
22.8
🚀 2024-05-14
79
Phi-3.5-MoE-instruct
Microsoft
Open livebench
Microsoft
20.9
📐 42.0B 🚀 2024-08-17
80
Phi-3-small-128k-instruct
Microsoft
Open livebench
Microsoft
18.8
📐 7.392B 🚀 2024-05-07
81
mathstral-7B-v0.1
Unknown
livebench
Unknown
18.4
—
82
Qwen2.5-7B-Instruct-Turbo
Alibaba
livebench
Alibaba
17.2
—
83
open-mistral-nemo
Mistral AI
livebench
Mistral AI
16.5
—
84
Mixtral-8x7B-Instruct-v0.1
Mistral AI
Open livebench
Mistral AI
16.0
📐 46.703B 🚀 2023-12-10
85
Qwen1.5-110B-Chat
Alibaba
Open livebench
Alibaba
15.3
📐 111.21B 🚀 2024-04-25
86
command-r-03-2024
Cohere
livebench
Cohere
15.1
🚀 2024-03-11
87
Phi-3-medium-128k-instruct
Microsoft
Open livebench
Microsoft
14.7
📐 13.96B 🚀 2024-05-07
88
Mistral-7B-Instruct-v0.3
Mistral AI
Open livebench
Mistral AI
13.4
📐 7.248B 🚀 2024-05-22
89
OpenHermes-2.5-Mistral-7B
Nous Research
Open livebench
Nous Research
12.8
📐 7.242B
90
Qwen1.5-72B-Chat
Alibaba
livebench
Alibaba
12.5
🚀 2024-01-30
91
olmo-2-1124-13b-instruct
Allen AI
livebench
Allen AI
12.5
🚀 2024-12-18
92
DeepSeek-Coder-V2-Lite-Instruct
DeepSeek
code livebench
DeepSeek
12.1
🚀 2024-06-17
93
Qwen2-7B-Instruct
Alibaba
Open livebench
Alibaba
11.2
📐 7.616B 🚀 2024-06-04
94
Phi-3.5-mini-instruct
Microsoft
Open livebench
Microsoft
10.7
📐 3.821B 🚀 2024-08-16
95
DeepSeek-V2-Lite-Chat
DeepSeek
livebench
DeepSeek
10.2
🚀 2024-05-06
96
Starling-LM-7B-beta
Nexusflow
livebench
Nexusflow
10.0
—
97
Mistral-7B-Instruct-v0.2
Mistral AI
Open livebench
Mistral AI
9.7
📐 7.242B 🚀 2023-12-11
98
vicuna-7b-v1.5
LMSYS
Open livebench
LMSYS
9.3
📐 7.0B
99
vicuna-7b-v1.5-16k
Unknown
livebench
Unknown
8.3
—
100
Llama-2-7b-chat-hf
Meta
Open livebench
Meta
6.8
📐 6.738B 🚀 2023-07-13
数据来源: LMSYS Chatbot Arena · HuggingFace Open LLM · LiveBench (每日自动更新) | 最后更新: