Skip to content
Back
Theme
AI model leaderboard: the best AI models you can run · whatmodel.sh
about the author
25 min read
Original article ↗
1
GPT-6 Astra
OpenAI
85
±1
api $20.00/M
1.1M
platform.openai.com ↗
+4
2
Claude Opus 5.5
Anthropic
85
±1
api $8.00/M
1M
docs.anthropic.com ↗
+1
3
GPT-6.1 Terra
OpenAI
84
±1
api $2.00/M
openai.com ↗
4
Gemini 4 Carbon
Google
83
±1
limited preview
5
GPT-6.1 Sol
OpenAI
83
±1
api $4.00/M
1.1M
developers.openai.com ↗
6
Claude Fable 5.1
Anthropic
82
±1
api $20.00/M
1M
docs.anthropic.com ↗
+1
7
Muse Wonder Full
Meta
82
±2
Muse Code only
1M
research.meta.ai ↗
8
Claude Sonnet 5.5
Anthropic
82
±1
api $4.00/M
1M
platform.claude.com ↗
9
Gemini 4 Argon
Google
81
±1
api $4.00/M
1M
ai.google.dev ↗
10
Claude Opus 5
Anthropic
81
±1
api $10.00/M
1M
docs.anthropic.com ↗
+11
11
GPT-6 Sol
OpenAI
80
±1
api $4.00/M
1.1M
platform.openai.com ↗
+1
12
GPT-5.5 Pro
OpenAI
80
±1
api $67.50/M
1.1M
developers.openai.com ↗
13
GPT-5.6 Sol
OpenAI
80
±1
api $8.00/M
1.1M
platform.openai.com ↗
+14
14
Claude Fable 5
Anthropic
79
±1
api $20.00/M
1M
docs.anthropic.com ↗
+5
15
Claude Mythos Preview (limited preview)
Anthropic
79
±1
†
limited preview
1M
16
GPT-5.4 Pro
OpenAI
79
±1
api $67.50/M
1.1M
developers.openai.com ↗
17
Muse Wonder
Meta
78
±1
api $8.00/M
1M
dev.meta.ai ↗
18
GPT-5.5
OpenAI
78
±0
api $11.25/M
1.1M
platform.openai.com ↗
+16
19
MiMo-V2.6-Pro
Xiaomi
77
±1
api $0.54/M
+local
~443GB
1M
mimo.mi.com ↗
20
DeepSeek V4.1 Flash 1017
DeepSeek
77
±1
api $0.26/M
1M
api-docs.deepseek.com ↗
21
GPT-5.6 Terra
OpenAI
77
±1
api $4.50/M
1.1M
platform.openai.com ↗
+5
22
Hy4 preview (770B-A49B)
Tencent
77
±1
api $1.25/M
+local
~248GB
1M
cloud.tencent.com ↗
23
Qwen3.8 Max (2.4T-A95B)
Alibaba
76
±1
api $3.00/M
+local
~380GB
262k
deepinfra.com ↗
+2
24
Claude Opus 4.8
Anthropic
76
±0
api $10.00/M
1M
docs.anthropic.com ↗
+11
25
GPT-5.4
OpenAI
76
±1
api $5.63/M
1.1M
platform.openai.com ↗
+14
26
Gemini 3.8 Flash
Google
76
±1
api $1.50/M
1M
ai.google.dev ↗
+5
27
Muse Spark 1.3
Meta
76
±1
api $2.00/M
1M
dev.meta.ai ↗
28
MiMo-V2.6-Flash (309B-A15B)
Xiaomi
76
±1
api $0.17/M
+local
~136GB
1M
mimo.mi.com ↗
29
DeepSeek V4.1 Flash
DeepSeek
76
±1
local
~512GB
~12 tok/s
1M
how to run ›
30
GPT-5.2 Pro
OpenAI
76
±1
api $57.75/M
400k
developers.openai.com ↗
31
Kimi K3
Moonshot AI
75
±1
api $6.00/M
+local
~884GB
1M
platform.moonshot.ai ↗
+7
32
Claude Haiku 5.5
Anthropic
75
±1
api $0.20/M
1M
platform.claude.com ↗
33
GPT-6 Luna
OpenAI
75
±1
api $0.20/M
1.1M
platform.openai.com ↗
34
GPT-5.6 Luna
OpenAI
75
±1
api $0.45/M
1.1M
platform.openai.com ↗
+4
35
Grok 4.6
SpaceXAI (xAI)
75
±1
api $3.00/M
500k
docs.x.ai ↗
36
Gemini 3.7 Flash
Google
75
±1
api $1.50/M
1M
ai.google.dev ↗
+3
37
DeepSeek V4 Pro (0813)
DeepSeek
75
±1
api $1.63/M
+local
~1010GB
1M
deepinfra.com ↗
+2
38
GLM-5.3
Z.ai
75
±1
api $2.15/M
+local
~239GB
1M
docs.z.ai ↗
39
Qwen3.8 Max (0902)
Alibaba
74
±1
api $3.00/M
1M
www.alibabacloud.com ↗
40
Muse Spark Open
Meta
74
±1
api $2.00/M
+local
~190GB
1M
fireworks.ai ↗
41
DeepSeek V3.2 Speciale
DeepSeek
74
±3
†
comparison only
42
Gemini 3.1 Pro (Preview)
Google
74
±0
api $4.50/M
1M
ai.google.dev ↗
+23
43
Muse Spark
Meta
74
±2
comparison only
44
Claude Opus 4.7
Anthropic
74
±1
api $10.00/M
1M
docs.anthropic.com ↗
+9
45
Grok 4.5
SpaceXAI (xAI)
74
±1
api $3.00/M
500k
docs.x.ai ↗
+1
46
Qwen3.8-Omni-Flash
Alibaba
74
±1
†
api $0.23/M
1M
www.alibabacloud.com ↗
47
DeepSeek V4 Flash Vision (Exp)
DeepSeek
74
±2
local
~104GB
1M
llama.cpp ›
48
Qwen3.8-Flash-Next
Alibaba
73
±1
local
~59GB
~27 tok/s
262k
llama.cpp ›
49
Claude Sonnet 5
Anthropic
73
±1
api $4.00/M
1M
docs.anthropic.com ↗
+5
50
Claude Opus 4.6
Anthropic
73
±1
api $10.00/M
1M
docs.anthropic.com ↗
+22
51
Muse Spark 1.1
Meta
73
±1
api $2.00/M
1M
dev.meta.ai ↗
52
Grok 4.7
SpaceXAI (xAI)
73
±1
api $3.00/M
500k
docs.x.ai ↗
53
Muse Spark 1.2
Meta
73
±1
api $2.00/M
1M
dev.meta.ai ↗
54
Step 5 Preview
StepFun
73
±1
comparison only
55
Gemini 3.5 Flash
Google
73
±1
api $3.38/M
1M
ai.google.dev ↗
+3
56
Qwen3.7 Max
Alibaba
73
±1
api $3.75/M
1M
deepinfra.com ↗
57
GPT-5.3-Codex
OpenAI
73
±1
api $4.81/M
400k
platform.openai.com ↗
58
DeepSeek V4 Flash (0731)
DeepSeek
72
±1
api $0.11/M
+local
~92GB
1M
deepinfra.com ↗
+2
59
GLM-5.3-Flash
Z.ai
72
±1
api $0.24/M
+local
~103GB
1M
docs.z.ai ↗
+2
60
GPT-5.2
OpenAI
72
±1
api $4.81/M
400k
platform.openai.com ↗
+21
61
Gemini 3.6 Flash
Google
72
±1
api $1.50/M
1M
ai.google.dev ↗
+2
62
GLM-5.2
Z.ai
72
±1
api $2.15/M
+local
~121GB
1M
docs.z.ai ↗
+6
63
Grok 4.20 Multi-Agent (0309)
SpaceXAI (xAI)
72
±2
api $1.56/M
1M
docs.x.ai ↗
64
Dola Seed 2.0 Pro
ByteDance
72
±2
comparison only
65
Hunyuan Hy3 (295B-A21B)
Tencent
72
±1
api $0.23/M
+local
~94GB
256k
deepinfra.com ↗
66
Qwen3.8 27B
Alibaba
72
±1
api $1.60/M
+local
~18GB
~6.7 tok/s
262k
console.groq.com ↗
+3
67
LongCat 2.0 (1.6T-A48B)
Meituan
72
±2
api $1.30/M
+local
~2155GB
1M
longcat.chat ↗
68
Kimi K2.6
Moonshot AI
72
±1
api $1.71/M
+local
~317GB
262k
platform.moonshot.ai ↗
+11
69
GPT-5 Pro
OpenAI
72
±1
api $41.25/M
400k
developers.openai.com ↗
70
Gemini 3 Pro (Preview)
Google
71
±1
comparison only
1M
+15
71
GPT-5
OpenAI
71
±1
api $3.44/M
400k
platform.openai.com ↗
+22
72
Mistral Large 4 (public preview)
Mistral
71
±1
api $2.06/M
1M
docs.mistral.ai ↗
73
Qwen3.6 Max Preview
Alibaba
71
±1
api $2.92/M
256k
www.alibabacloud.com ↗
74
Claude Sonnet 4.6
Anthropic
71
±1
api $6.00/M
1M
docs.anthropic.com ↗
+18
75
Gemini 3 Flash (Preview)
Google
71
±1
api $1.13/M
1M
ai.google.dev ↗
+8
76
DeepSeek V4 Pro (Preview, Apr 2026)
DeepSeek
71
±1
local
~604GB
llama.cpp ›
+6
77
Claude Opus 4.5
Anthropic
71
±1
api $10.00/M
200k
docs.anthropic.com ↗
+14
78
Qwen3.7 Plus
Alibaba
71
±1
api $0.70/M
1M
www.alibabacloud.com ↗
79
Kimi K2.7 Code
Moonshot AI
71
±1
api $1.71/M
+local
~359GB
262k
platform.kimi.ai ↗
80
North Small Translate 1.0
Cohere
71
±5
†
api price unknown
16k
docs.cohere.com ↗
81
Solar Open 2 (250B-A15B)
Upstage
71
±1
†
local
~527GB
1M
how to run ›
82
DeepSeek V4 Flash (Preview, Apr 2026)
DeepSeek
70
±1
local
~103GB
llama.cpp ›
+4
83
Grok 4.20 (0309 reasoning)
SpaceXAI (xAI)
70
±1
api $1.56/M
1M
docs.x.ai ↗
84
Beam 1.0 501B A23B
Reflection
70
±1
api price unknown
1M
developers.reflection.ai ↗
85
GPT-5.4 mini
OpenAI
70
±1
api $1.69/M
400k
platform.openai.com ↗
+6
86
Ling 3.0 Flash (124B-A5B)
inclusionAI (Ant Group)
70
±2
†
api $0.090/M
+local
~71GB
131k
deepinfra.com ↗
87
GPT-5.1
OpenAI
70
±1
api $3.44/M
400k
platform.openai.com ↗
+8
88
GLM-5.1
Z.ai
70
±0
api $2.15/M
+local
~119GB
200k
docs.z.ai ↗
+11
89
o3-pro
OpenAI
70
±2
api $35.00/M
200k
developers.openai.com ↗
90
Qwen3.5 397B-A17B
Alibaba
69
±0
api $1.09/M
+local
~65GB
262k
deepinfra.com ↗
+15
91
Gemini 2.5 Pro Preview (06-05)
Google
69
±2
comparison only
92
KAT-Coder-V2.5-Dev (35B-A3B)
Kuaishou (Kwaipilot)
69
±2
†
local
~21GB
262k
LM Studio ›
93
Ornith 1.5 35B-A3B
DeepReinforce
69
±1
†
local
~21GB
~80 tok/s
262k
LM Studio ›
94
Grok 4.3
SpaceXAI (xAI)
69
±1
api $1.56/M
1M
docs.x.ai ↗
95
MiniMax-M3
MiniMax
69
±1
api $0.48/M
+local
~131GB
1M
deepinfra.com ↗
+2
96
Qwen3.6 Plus
Alibaba
69
±1
api $1.13/M
1M
docs.together.ai ↗
+1
97
Kimi K2.5
Moonshot AI
69
±1
api $1.20/M
+local
~160GB
262k
docs.aws.amazon.com ↗
+15
98
MiMo-V2-Pro
Xiaomi
69
±1
comparison only
99
Qwen3-Max (2026-01-23)
Alibaba
69
±1
†
comparison only
100
GLM-5
Z.ai
69
±1
api $1.55/M
+local
~119GB
205k
docs.z.ai ↗
+11
101
MiMo-V2.5-Pro (1T-A42B)
Xiaomi
69
±1
api $0.65/M
+local
~163GB
1M
novita.ai ↗
102
Muse Glimmer 30B
Meta
69
±1
api $0.64/M
+local
~18GB
~27 tok/s
131k
fireworks.ai ↗
103
o3
OpenAI
68
±1
api $3.50/M
200k
platform.openai.com ↗
+11
104
Inkling Small (266B-A12B)
Thinking Machines
68
±1
api $0.64/M
+local
~86GB
1M
deepinfra.com ↗
105
Nemotron 3 Ultra 550B-A55B
NVIDIA
68
±1
api $1.35/M
+local
~89GB
1M
docs.together.ai ↗
106
Qwen3.6 27B
Alibaba
68
±1
api $1.20/M
+local
~18GB
~16 tok/s
262k
console.groq.com ↗
+4
107
Ring-2.6-1T
inclusionAI (Ant Group)
68
±2
†
comparison only
108
A.X K2 (688B-A33B)
SK Telecom
68
±1
†
local
~1454GB
262k
how to run ›
109
MiMo-V2.5 (310B-A15B)
Xiaomi
68
±1
api $0.21/M
+local
~100GB
1M
novita.ai ↗
110
Qwen3.5 Plus
Alibaba
68
±2
api $0.90/M
1M
www.alibabacloud.com ↗
111
GPT-5.5 Instant
OpenAI
68
±1
comparison only
112
Gemini 3.5 Flash-Lite
Google
68
±1
api $0.85/M
1M
ai.google.dev ↗
113
Qwen3.5 122B-A10B
Alibaba
68
±1
api $1.10/M
+local
~71GB
262k
www.alibabacloud.com ↗
+5
114
Inkling (975B-A41B)
Thinking Machines
68
±1
api $1.73/M
+local
~156GB
1M
deepinfra.com ↗
115
Claude Sonnet 4.5
Anthropic
68
±1
api $6.00/M
200k
docs.anthropic.com ↗
+19
116
GLM-5V-Turbo
Z.ai
68
±2
api $1.90/M
200k
www.siliconflow.com ↗
117
LongCat-Flash-Thinking (560B-A27B)
Meituan
68
±1
†
comparison only
128k
118
Nemotron 3.5 Bolt 74B A9B
NVIDIA
68
±2
†
local
~157GB
262k
how to run ›
119
GPT-5.4 nano
OpenAI
68
±1
api $0.46/M
400k
platform.openai.com ↗
+1
120
GLM-4.7
Z.ai
68
±1
api $1.00/M
+local
~58GB
205k
docs.z.ai ↗
+5
121
Qwen3.5 27B
Alibaba
68
±0
api $0.84/M
+local
~18GB
~29 tok/s
262k
deepinfra.com ↗
+9
122
Gemini 2.5 Pro Experimental (03-25)
Google
67
±2
comparison only
123
Grok 4 (0709)
SpaceXAI (xAI)
67
±1
comparison only
+1
124
MiMo-V2-Omni
Xiaomi
67
±2
comparison only
262k
125
Nemotron 3.5 Super VL 120B A12B
NVIDIA
67
±1
local
~254GB
1M
how to run ›
126
DeepSeek V3.2
DeepSeek
67
±1
api $0.29/M
+local
~110GB
128k
deepinfra.com ↗
+15
127
Step 3.5 Flash (196B-A11B)
StepFun
67
±1
api $0.15/M
+local
~118GB
~18 tok/s
256k
platform.stepfun.ai ↗
128
GPT-5.2-Codex
OpenAI
67
±2
comparison only
129
Qwen3.6 35B-A3B
Alibaba
67
±1
api $0.31/M
+local
~21GB
~63 tok/s
262k
deepinfra.com ↗
+5
130
Qwen3-Coder-Next (80B-A3B)
Alibaba
67
±2
api $0.60/M
+local
~25GB
~62 tok/s
262k
www.alibabacloud.com ↗
131
GPT-5 mini
OpenAI
67
±1
api $0.69/M
400k
platform.openai.com ↗
+16
132
MiniMax-M2.7
MiniMax
67
±1
api $0.53/M
+local
~75GB
205k
platform.minimax.io ↗
+2
133
Ornith 1.0 35B (35B-A3B)
DeepReinforce
67
±1
local
~23GB
~103 tok/s
262k
LM Studio ›
134
Claude Opus 4
Anthropic
67
±1
comparison only
+4
135
Gemini 2.5 Pro
Google
66
±1
api $3.44/M
1M
ai.google.dev ↗
+16
136
Gemma 4 31B
Google
66
±1
api $0.19/M
+local
~24GB
~11 tok/s
262k
deepinfra.com ↗
+21
137
Claude Opus 4.1
Anthropic
66
±1
comparison only
+2
138
Hy3 preview (295B-A21B)
Tencent
66
±1
local
~629GB
how to run ›
139
Kimi K2 Thinking
Moonshot AI
66
±1
api $1.07/M
+local
~160GB
262k
docs.aws.amazon.com ↗
140
Gemini 2.5 Pro Preview (05-06)
Google
66
±1
comparison only
+2
141
Gemini 2.5 Pro Preview (03-25)
Google
66
±2
comparison only
142
K-EXAONE 2.0 (750B-A37B)
LG AI Research
66
±1
†
local
~791GB
262k
how to run ›
143
Gemini 3.1 Flash-Lite
Google
66
±1
api $0.56/M
1M
ai.google.dev ↗
144
Qwen3.7 Flash
Alibaba
66
±1
api $0.055/M
1M
www.alibabacloud.com ↗
145
Laguna M.1
Poolside
66
±2
api price unknown
+local
~135GB
262k
huggingface.co ↗
146
DeepSeek V3.1 Terminus
DeepSeek
66
±1
local
~230GB
164k
llama.cpp ›
147
DeepSeek V3.2 Exp
DeepSeek
66
±1
local
~726GB
how to run ›
148
Kimi K2 Instruct (0711)
Moonshot AI
66
±1
api $1.00/M
+local
~152GB
131k
novita.ai ↗
+3
149
o1 (2024-12-17)
OpenAI
66
±1
api $26.25/M
200k
developers.openai.com ↗
+13
150
GigaChat 3.5 Ultra Reasoning (432B-A28B)
Sber
66
±1
†
local
~461GB
262k
how to run ›
151
o4-mini
OpenAI
66
±1
api $1.93/M
200k
platform.openai.com ↗
+12
152
Qwen3 235B-A22B Thinking 2507
Alibaba
66
±1
api $0.97/M
+local
~76GB
131k
novita.ai ↗
+6
153
Qwen3.5 35B-A3B
Alibaba
66
±0
api $0.35/M
+local
~21GB
~50 tok/s
262k
deepinfra.com ↗
+13
154
Step 3.7 Flash (198B-A11B)
StepFun
66
±1
api $0.44/M
+local
~104GB
256k
platform.stepfun.ai ↗
155
Grok 4.1 Fast (Reasoning)
SpaceXAI (xAI)
66
±1
api $0.28/M
128k
azure.microsoft.com ↗
+4
156
LongCat-Flash-Chat (560B-A27B)
Meituan
66
±1
local
~333GB
128k
LM Studio ›
157
Qwen3.6 Flash
Alibaba
65
±1
api $0.56/M
1M
www.alibabacloud.com ↗
158
Spark-X2.5 4B
iFLYTEK (SparkLLM)
65
±1
†
local
~3.5GB
~114 tok/s
1M
LM Studio ›
159
DeepSeek V3.1
DeepSeek
65
±1
api $0.42/M
+local
~110GB
131k
deepinfra.com ↗
+3
160
GLM-4.6
Z.ai
65
±1
api $1.00/M
+local
~58GB
205k
docs.z.ai ↗
+1
161
Claude Sonnet 4
Anthropic
65
±1
comparison only
+12
162
Qwen3-Max (2025-09-23)
Alibaba
65
±1
api $2.40/M
262k
www.alibabacloud.com ↗
163
MiniMax-M2.5
MiniMax
65
±1
api $0.53/M
+local
~75GB
205k
platform.minimax.io ↗
+3
164
o3-mini
OpenAI
65
±1
api $1.93/M
200k
developers.openai.com ↗
+13
165
MiMo-V2-Flash (309B-A15B)
Xiaomi
65
±1
local
~103GB
llama.cpp ›
166
DeepSeek R1 0528
DeepSeek
65
±1
api $0.91/M
+local
~104GB
164k
deepinfra.com ↗
+6
167
Claude 3.7 Sonnet
Anthropic
65
±1
comparison only
+16
168
MiniMax-M2.1
MiniMax
65
±1
local
~79GB
llama.cpp ›
169
ChatGPT-4o (2025-03-26)
OpenAI
65
±2
comparison only
170
Nemotron Cascade 2 30B-A3B
NVIDIA
65
±1
local
~20GB
~90 tok/s
256k
LM Studio ›
171
MiMo-V2.6-Distill-Qwen-9B
Xiaomi
64
±2
†
local
~7.8GB
LM Studio ›
172
Laguna XS 2.1 (33B-A3B)
Poolside
64
±2
†
local
~21GB
262k
LM Studio ›
173
K-EXAONE (236B-A23B)
LG AI Research
64
±1
local
~152GB
262k
llama.cpp ›
174
Qwen3 235B-A22B Instruct 2507
Alibaba
64
±1
api $0.20/M
+local
~73GB
~15 tok/s
262k
deepinfra.com ↗
+3
175
Mistral Medium 3.5 (128B)
Mistral
64
±1
api $3.00/M
+local
~43GB
262k
docs.mistral.ai ↗
176
INTELLECT-3
Prime Intellect
64
±1
local
~48GB
llama.cpp ›
177
GLM-4.5
Z.ai
64
±1
api $1.00/M
+local
~58GB
131k
docs.z.ai ↗
+3
178
Qwen3.5 Flash
Alibaba
64
±1
api $0.17/M
1M
www.alibabacloud.com ↗
179
MiniMax-M2
MiniMax
64
±1
api $0.53/M
+local
~75GB
205k
docs.aws.amazon.com ↗
180
Mistral Medium 3.1 (2508)
Mistral
64
±2
comparison only
181
Command A+ (05-2026)
Cohere
64
±1
api price unknown
+local
~71GB
128k
docs.cohere.com ↗
182
Claude Haiku 4.5
Anthropic
64
±1
api $2.00/M
200k
docs.anthropic.com ↗
+9
183
Nemotron 3 Super 120B-A12B
NVIDIA
64
±1
api $0.28/M
+local
~73GB
~20 tok/s
262k
docs.aws.amazon.com ↗
184
Laguna XS.2
Poolside
64
±1
local
~21GB
262k
LM Studio ›
185
Gemma 4 26B-A4B
Google
64
±1
api $0.14/M
+local
~18GB
~55 tok/s
262k
deepinfra.com ↗
+13
186
Solar Pro 4
Upstage
64
±1
api $0.53/M
524k
developers.upstage.ai ↗
187
EXAONE 4.5 33B
LG AI Research
64
±2
†
local
~24GB
262k
llama.cpp ›
188
Kimi K2 Instruct (0905)
Moonshot AI
63
±2
local
~298GB
llama.cpp ›
189
Qwen3-Coder 480B-A35B Instruct
Alibaba
63
±1
api $0.67/M
+local
~78GB
262k
novita.ai ↗
190
Grok 3 Mini Beta
SpaceXAI (xAI)
63
±1
comparison only
+2
191
Qwen3-VL 235B-A22B Thinking
Alibaba
63
±1
local
~106GB
256k
LM Studio ›
192
DeepSeek R1 (Jan '25)
DeepSeek
63
±1
api $4.00/M
+local
~104GB
128k
docs.together.ai ↗
+15
193
o1-preview
OpenAI
63
±1
comparison only
+7
194
Grok 3 Beta
SpaceXAI (xAI)
63
±1
comparison only
195
Qwen3-VL 235B-A22B Instruct
Alibaba
63
±1
local
~128GB
256k
LM Studio ›
196
MiniCPM5 2B
OpenBMB
63
±1
†
local
~2.4GB
131k
LM Studio ›
197
Nemotron-Labs-3 Puzzle 75B-A9B
NVIDIA
63
±1
†
local
~35GB
llama.cpp ›
198
Qwen3-Next 80B-A3B Instruct
Alibaba
63
±1
api $0.34/M
+local
~26GB
~55 tok/s
131k
deepinfra.com ↗
199
Nova 2 Pro (Preview)
Amazon
63
±2
api $3.78/M
1M
aws.amazon.com ↗
200
Gemini 2.5 Flash Preview (09-2025)
Google
63
±1
comparison only
201
Qwen3-Next 80B-A3B Thinking
Alibaba
63
±1
api $0.41/M
+local
~25GB
131k
www.alibabacloud.com ↗
+3
202
Granite 4.2 30B
IBM
63
±1
api $0.28/M
+local
~19GB
131k
deepinfra.com ↗
203
GPT-4.5 Preview
OpenAI
63
±1
comparison only
+6
204
Gemini 2.5 Flash Preview (04-17)
Google
63
±1
comparison only
205
GPT-4.1
OpenAI
62
±1
api $3.50/M
1M
platform.openai.com ↗
+17
206
GLM-4.5-Air
Z.ai
62
±1
api $0.42/M
+local
~35GB
~23 tok/s
131k
docs.z.ai ↗
+4
207
Trinity-Large-Thinking
Arcee AI
62
±2
api $0.39/M
+local
~141GB
512k
docs.arcee.ai ↗
208
Qwen3.5 9B
Alibaba
62
±0
api $0.11/M
+local
~6.7GB
~22 tok/s
262k
deepinfra.com ↗
+19
209
Nemotron 3.5 Lightning 30B-A3B
NVIDIA
62
±2
api $0.087/M
+local
~20GB
~64 tok/s
262k
fireworks.ai ↗
210
Seed-OSS 36B Instruct
ByteDance Seed
62
±1
local
~23GB
524k
LM Studio ›
211
Gemma 4 12B
Google
62
±1
local
~9.2GB
~29 tok/s
262k
LM Studio ›
212
HyperCLOVA X SEED 32B Think
NAVER Cloud
62
±2
†
comparison only
128k
213
MiniMax-M1 (80k)
MiniMax
62
±1
api $0.96/M
+local
~959GB
1M
novita.ai ↗
214
GLM-4.6V
Z.ai
62
±2
api $0.45/M
+local
~50GB
128k
docs.z.ai ↗
215
Magistral Medium 1.2 (2509)
Mistral
62
±2
†
comparison only
128k
216
Gemini 2.5 Flash
Google
62
±1
api $0.85/M
1M
ai.google.dev ↗
+10
217
Gemini 2.5 Flash Preview (05-20)
Google
62
±1
comparison only
+1
218
Gemini 2.0 Flash-Lite (001)
Google
62
±2
comparison only
219
Qwen3-VL 32B Thinking
Alibaba
62
±1
api $0.28/M
+local
~22GB
256k
www.alibabacloud.com ↗
220
gpt-oss-120b
OpenAI
62
±1
api $0.26/M
+local
~64GB
~56 tok/s
131k
console.groq.com ↗
+19
221
GPT-5 nano
OpenAI
62
±1
api $0.14/M
400k
platform.openai.com ↗
+7
222
Mistral Large 3 (675B-A41B)
Mistral
62
±1
api $0.75/M
+local
~108GB
262k
docs.mistral.ai ↗
+1
223
Apriel 1.6 15B Thinker
ServiceNow
62
±1
†
local
~10GB
LM Studio ›
224
Devstral 2 (2512)
Mistral
62
±2
local
~74GB
256k
LM Studio ›
225
Gemini 2.5 Flash-Lite Preview (06-17)
Google
62
±2
comparison only
226
A.X K1 (519B-A33B)
SK Telecom
61
±1
†
local
~1091GB
how to run ›
227
o1-mini
OpenAI
61
±1
comparison only
+12
228
GLM-4.5V
Z.ai
61
±2
api $0.90/M
+local
~69GB
64k
docs.z.ai ↗
229
Devstral Small 2 24B
Mistral
61
±2
local
~16GB
262k
llama.cpp ›
230
MiniMax-M1 (40k)
MiniMax
61
±1
†
comparison only
231
Llama 3.1 Nemotron Ultra 253B v1
NVIDIA
61
±1
local
~82GB
128k
llama.cpp ›
232
Gemini 2.0 Pro Experimental (02-05)
Google
61
±1
comparison only
233
Grok 4 Fast
SpaceXAI (xAI)
61
±1
comparison only
234
DeepSeek V3 0324
DeepSeek
60
±1
local
~102GB
164k
llama.cpp ›
+11
235
Claude 3.5 Sonnet (2024-10-22)
Anthropic
60
±1
comparison only
+14
236
Gemini 2.0 Flash (001)
Google
60
±1
comparison only
+7
237
GPT-4.1 mini
OpenAI
60
±1
api $0.70/M
1M
platform.openai.com ↗
+13
238
Qwen3 30B-A3B Instruct 2507
Alibaba
60
±1
api $0.15/M
+local
~19GB
~100 tok/s
262k
tokenfactory.nebius.com ↗
+4
239
Qwen3 30B-A3B Thinking 2507
Alibaba
60
±1
api $0.75/M
+local
~19GB
262k
www.alibabacloud.com ↗
+8
240
ERNIE 4.5 300B-A47B
Baidu
60
±1
†
local
~97GB
131k
llama.cpp ›
241
Qwen3.5 4B
Alibaba
60
±1
local
~3.8GB
262k
llama.cpp ›
+11
242
Mistral Medium 3 (2505)
Mistral
60
±1
comparison only
243
Mellum2.1 12B-A2.5B Thinking
JetBrains
60
±1
†
local
~8.3GB
LM Studio ›
244
Gemma 2 9B IT SimPO
Princeton NLP
60
±1
local
~7.6GB
llama.cpp ›
245
Gemma 2 9B IT DPO (Princeton)
Princeton NLP
60
±1
local
~7.6GB
llama.cpp ›
246
Falcon-H1R 7B
TII
60
±1
†
local
~5.3GB
262k
LM Studio ›
247
Nemotron-Cascade-14B-Thinking
NVIDIA
60
±1
†
local
~10GB
LM Studio ›
248
Qwen3-VL 32B Instruct
Alibaba
60
±1
api $0.28/M
+local
~22GB
256k
www.alibabacloud.com ↗
249
DeepSeek V3 (Dec '24)
DeepSeek
60
±1
api $0.46/M
+local
~337GB
131k
deepinfra.com ↗
+10
250
Qwen3 235B-A22B (Apr 2025, hybrid)
Alibaba
60
±0
api $1.23/M
+local
~73GB
131k
www.alibabacloud.com ↗
+14
251
Gemini 2.0 Flash-Lite Preview (02-05)
Google
60
±2
comparison only
252
Mistral Small 4 (119B-A6.5B)
Mistral
60
±2
api $0.26/M
+local
~37GB
262k
docs.mistral.ai ↗
253
Granite 4.2 8B
IBM
59
±1
api $0.11/M
+local
~6.8GB
131k
wandb.ai ↗
254
QwQ-32B
Alibaba
59
±1
local
~21GB
131k
LM Studio ›
+7
255
Solar Open 100B (102B-A12B)
Upstage
59
±1
†
local
~41GB
131k
llama.cpp ›
256
Qwen3-VL 30B-A3B Thinking
Alibaba
59
±1
api $0.75/M
+local
~20GB
256k
www.alibabacloud.com ↗
257
Trinity-Large-Preview
Arcee AI
59
±2
local
~155GB
llama.cpp ›
258
OpenReasoning-Nemotron-32B
NVIDIA
59
±2
†
local
~21GB
LM Studio ›
259
EXAONE 4.0 32B
LG AI Research
59
±1
local
~20GB
131k
LM Studio ›
260
Phi-4-reasoning-plus 14B
Microsoft
59
±1
local
~10GB
LM Studio ›
261
GLM-4.7-Flash
Z.ai
58
±1
api $0.0000/M
+local
~18GB
~44 tok/s
200k
docs.z.ai ↗
+1
262
Mercury 2
Inception
58
±2
comparison only
263
gpt-oss-20b
OpenAI
58
±1
api $0.13/M
+local
~13GB
~79 tok/s
131k
console.groq.com ↗
+16
264
Olmo 3.1 32B Think
Ai2
58
±1
local
~21GB
66k
LM Studio ›
265
DiffusionGemma 26B-A4B
Google
58
±1
†
comparison only
262k
266
Qwen3 14B
Alibaba
58
±1
api $0.61/M
+local
~10GB
33k
www.alibabacloud.com ↗
+7
267
Llama 3.3 Nemotron Super 49B v1
NVIDIA
58
±2
local
~22GB
llama.cpp ›
268
DeepSeek R1 Distill Llama 70B
DeepSeek
58
±1
api $0.80/M
+local
~30GB
131k
novita.ai ↗
+1
269
GPT-4o (2024-08-06)
OpenAI
58
±1
api $4.38/M
128k
developers.openai.com ↗
+23
270
Nemotron-Cascade-8B
NVIDIA
58
±1
†
local
~6.3GB
LM Studio ›
271
Command A (03-2025)
Cohere
58
±1
api $4.38/M
+local
~37GB
256k
azure.microsoft.com ↗
272
Olmo 3 32B Think
Ai2
58
±1
local
~21GB
66k
LM Studio ›
273
GPT-4o (2024-05-13)
OpenAI
58
±0
api $7.50/M
128k
developers.openai.com ↗
+19
274
Phi-4-reasoning 14B
Microsoft
58
±1
api $0.22/M
+local
~10GB
33k
azure.microsoft.com ↗
275
Claude 3.5 Sonnet (2024-06-20)
Anthropic
58
±0
comparison only
+16
276
Nova 2 Lite
Amazon
58
±1
api $0.94/M
1M
docs.aws.amazon.com ↗
277
Magistral Small 1.2
Mistral
58
±1
api $0.75/M
+local
~16GB
131k
docs.aws.amazon.com ↗
278
GPT-4o (2024-11-20)
OpenAI
58
±1
api $4.38/M
128k
developers.openai.com ↗
+7
279
Qwen3-VL 8B Thinking
Alibaba
58
±1
api $0.66/M
+local
~6.9GB
256k
www.alibabacloud.com ↗
280
Qwen3 32B
Alibaba
58
±0
api $0.13/M
+local
~20GB
131k
deepinfra.com ↗
+17
281
Gemini 2.0 Flash Thinking Experimental (01-21)
Google
58
±1
comparison only
282
Qwen2.5-Max (2025-01-25)
Alibaba
58
±1
comparison only
283
Qwen3-VL 30B-A3B Instruct
Alibaba
58
±1
api $0.35/M
+local
~20GB
256k
www.alibabacloud.com ↗
284
Qwen3 Coder 30B-A3B Instruct
Alibaba
57
±1
api $0.12/M
+local
~19GB
~93 tok/s
160k
novita.ai ↗
285
Qwen2.5 Coder 32B Instruct
Alibaba
57
±1
api $0.74/M
+local
~21GB
131k
developers.cloudflare.com ↗
+5
286
Gemini 2.5 Flash-Lite
Google
57
±2
api $0.17/M
1M
ai.google.dev ↗
+1
287
Llama 4 Maverick (402B-A17B)
Meta
57
±1
api $0.42/M
+local
~65GB
1M
docs.aws.amazon.com ↗
+14
288
DeepSeek R1 0528 Qwen3 8B
DeepSeek
57
±1
api $0.068/M
+local
~6.5GB
~21 tok/s
128k
novita.ai ↗
289
Gemini 1.5 Pro Experimental (0827)
Google
57
±1
comparison only
290
Granite 4.2 3B
IBM
57
±1
api $0.052/M
+local
~3.3GB
131k
deepinfra.com ↗
291
Gemini 1.5 Pro (002)
Google
57
±1
comparison only
+5
292
Llama 3.3 Nemotron Super 49B v1.5
NVIDIA
57
±1
local
~18GB
131k
llama.cpp ›
293
Nemotron 3 Nano 30B-A3B
NVIDIA
57
±1
api $0.087/M
+local
~20GB
~90 tok/s
262k
deepinfra.com ↗
+3
294
Athene-V2-Chat 72B
Nexusflow
57
±1
local
~44GB
33k
LM Studio ›
295
Grok 2 (1212)
SpaceXAI (xAI)
57
±1
comparison only
296
Granite 4.1 30B
IBM
57
±1
†
local
~19GB
~25 tok/s
Ollama ›
297
Nemotron-Cascade-8B-Thinking
NVIDIA
57
±2
local
~6.3GB
LM Studio ›
298
Gemini 2.0 Flash Experimental
Google
57
±1
comparison only
299
Qwen2.5-Omni 7B
Alibaba
57
±2
local
~5.8GB
llama.cpp ›
300
Sky-T1 32B Preview
NovaSky (UC Berkeley)
57
±4
local
~21GB
LM Studio ›
301
Ministral 3 14B Reasoning 2512
Mistral
57
±1
local
~10GB
262k
llama.cpp ›
302
Qwen Plus (2025-01-25)
Alibaba
57
±1
api $0.60/M
131k
www.alibabacloud.com ↗
303
Mistral Small 3.2 24B
Mistral
56
±1
api $0.11/M
+local
~15GB
128k
deepinfra.com ↗
+4
304
DeepSeek-V2.5 (1210)
DeepSeek
56
±1
local
~82GB
llama.cpp ›
305
QED-Nano
LM Provers
56
±2
local
~4.1GB
262k
llama.cpp ›
306
Qwen3 4B Thinking 2507
Alibaba
56
±1
local
~4.2GB
~67 tok/s
262k
LM Studio ›
+3
307
GPT-4 Turbo (2024-04-09)
OpenAI
56
±0
api $15.00/M
128k
developers.openai.com ↗
+18
308
Yi-Lightning
01.AI
56
±1
api price unknown
16k
platform.lingyiwanwu.com ↗
309
Gemini 1.5 Pro Experimental (0801)
Google
56
±1
comparison only
310
Qwen3-VL 4B Thinking
Alibaba
56
±1
local
~4.4GB
256k
llama.cpp ›
311
Qwen2.5 72B Instruct
Alibaba
56
±1
api $0.37/M
+local
~31GB
33k
deepinfra.com ↗
+24
312
Qwen2.5-VL 72B Instruct
Alibaba
56
±1
local
~46GB
33k
LM Studio ›
+3
313
Llama 3.1 405B Instruct
Meta
56
±1
api $2.40/M
+local
~160GB
128k
docs.aws.amazon.com ↗
+13
314
Mistral Large 2 (2411)
Mistral
56
±1
local
~77GB
128k
llama.cpp ›
+8
315
Qwen2.5 Coder 14B Instruct
Alibaba
56
±1
local
~11GB
~18 tok/s
131k
LM Studio ›
316
DeepSeek R1 Distill Qwen 32B
DeepSeek
56
±1
api $1.59/M
+local
~21GB
~7.3 tok/s
131k
developers.cloudflare.com ↗
+5
317
Qwen2.5 32B Instruct
Alibaba
56
±1
local
~21GB
131k
LM Studio ›
+11
318
Qwen3 8B
Alibaba
56
±1
api $0.31/M
+local
~6.3GB
~25 tok/s
33k
www.alibabacloud.com ↗
+15
319
DeepSeek R1 Distill Qwen 14B
DeepSeek
56
±1
local
~11GB
~15 tok/s
131k
LM Studio ›
+2
320
Magistral Medium 1.0 (2506)
Mistral
56
±1
comparison only
321
Molmo 2 8B
Ai2
56
±2
local
~6.8GB
llama.cpp ›
322
Ministral 3 14B
Mistral
55
±1
api $0.20/M
+local
~9.1GB
~46 tok/s
262k
docs.mistral.ai ↗
+2
323
Nemotron Nano 9B v2
NVIDIA
55
±1
api $0.10/M
+local
~7.6GB
131k
docs.aws.amazon.com ↗
324
EXAONE Deep 32B
LG AI Research
55
±2
†
local
~22GB
33k
Ollama ›
325
Qwen3 4B Instruct 2507
Alibaba
55
±1
local
~4.2GB
~107 tok/s
262k
LM Studio ›
+4
326
Qwen3 30B-A3B (Apr 2025, hybrid)
Alibaba
55
±0
api $0.35/M
+local
~18GB
33k
www.alibabacloud.com ↗
+10
327
Bielik 11B v3.0 Instruct
SpeakLeash
55
±2
local
~8.1GB
LM Studio ›
328
Nova Premier
Amazon
55
±2
†
api $5.00/M
1M
aws.amazon.com ↗
329
Granite 4.1 8B
IBM
55
±1
api $0.11/M
+local
~7.1GB
~70 tok/s
131k
replicate.com ↗
330
Magistral Small 1.0 (2506)
Mistral
55
±1
local
~16GB
128k
LM Studio ›
331
Spark-X2.5 1.7B
iFLYTEK (SparkLLM)
55
±1
†
local
~1.9GB
~166 tok/s
1M
llama.cpp ›
332
Qwen2.5-Math 72B Instruct
Alibaba
55
±2
†
local
~44GB
4k
LM Studio ›
333
Llama 3.3 70B Instruct
Meta
55
±1
api $0.72/M
+local
~25GB
~13 tok/s
128k
docs.aws.amazon.com ↗
+21
334
Magistral Medium 1.1 (2507)
Mistral
55
±1
†
comparison only
40k
335
Qwen3-VL 8B Instruct
Alibaba
55
±1
api $0.31/M
+local
~6.9GB
256k
www.alibabacloud.com ↗
336
Mistral Large 2 (2407)
Mistral
55
±1
local
~45GB
128k
llama.cpp ›
+10
337
Falcon-H1 34B Instruct
TII
55
±3
local
~23GB
262k
llama.cpp ›
338
Llama 4 Scout (109B-A17B)
Meta
55
±1
api $0.15/M
+local
~36GB
~19 tok/s
328k
deepinfra.com ↗
+8
339
GPT-4 Turbo Preview (1106)
OpenAI
55
±1
comparison only
+5
340
Bielik 11B v2.6 Instruct
SpeakLeash
55
±3
local
~8.1GB
LM Studio ›
341
Mistral Small 3.1 24B (2503)
Mistral
55
±1
local
~16GB
128k
llama.cpp ›
+7
342
Llama 3.1 Tulu 3 70B
Ai2
55
±1
local
~43GB
131k
LM Studio ›
343
Pixtral Large (2411)
Mistral
55
±3
local
~51GB
llama.cpp ›
344
Olmo 3.1 32B Instruct
Ai2
55
±2
local
~21GB
66k
LM Studio ›
345
GigaChat 3.5 Ultra Instruct (432B-A28B)
Sber
55
±1
†
local
~457GB
262k
how to run ›
346
GPT-4 Turbo Preview (0125)
OpenAI
55
±1
comparison only
+3
347
DeepSeek-V2.5
DeepSeek
55
±1
local
~151GB
164k
Ollama ›
+1
348
OpenThinker2 32B
Open Thoughts
55
±1
local
~21GB
33k
LM Studio ›
349
DeepSeek-V2 Chat (0628)
DeepSeek
55
±1
local
~66GB
llama.cpp ›
350
Claude 3.5 Haiku
Anthropic
55
±1
comparison only
+9
351
OpenThinker 32B
Open Thoughts
55
±1
†
local
~21GB
33k
LM Studio ›
352
Command A Reasoning (08-2025)
Cohere
54
±2
local
~34GB
llama.cpp ›
353
Magistral Small 1.1 (2507)
Mistral
54
±1
†
local
~16GB
40k
LM Studio ›
354
Mellum2 12B-A2.5B Thinking
JetBrains
54
±1
†
local
~8.6GB
131k
LM Studio ›
355
Ministral 3 8B Reasoning 2512
Mistral
54
±1
local
~6.5GB
262k
LM Studio ›
356
Llama 3.1 Tulu 3 70B DPO
Ai2
54
±1
local
~22GB
131k
llama.cpp ›
357
Gemini 1.5 Flash Experimental (0827)
Google
54
±1
comparison only
358
Nemotron 3 Nano 4B
NVIDIA
54
±1
local
~2.9GB
~52 tok/s
262k
LM Studio ›
359
GPT-4o mini (2024-07-18)
OpenAI
54
±0
api $0.26/M
128k
developers.openai.com ↗
+32
360
DeepSeek-Coder-V2 Instruct (0614)
DeepSeek
54
±1
local
~92GB
llama.cpp ›
+2
361
Gemini 1.5 Pro (001)
Google
54
±1
comparison only
+3
362
DeepSeek-Coder-V2 Instruct (0724)
DeepSeek
54
±1
local
~151GB
llama.cpp ›
363
Mistral Small 3 24B (2501)
Mistral
54
±1
local
~15GB
32k
LM Studio ›
+6
364
GPT-4 (0314)
OpenAI
54
±1
comparison only
+21
365
Gemini 1.5 Flash (002)
Google
54
±1
comparison only
+5
366
Qwen Turbo (2024-11-01)
Alibaba
54
±2
comparison only
367
GLM-4 9B Chat 1M
Zhipu AI (THUDM)
54
±4
local
~8.1GB
1M
llama.cpp ›
368
EXAONE Deep 7.8B
LG AI Research
54
±2
†
local
~6.5GB
33k
llama.cpp ›
369
Claude 3 Opus
Anthropic
54
±0
comparison only
+15
370
Yi-Large Preview
01.AI
54
±1
comparison only
371
Qwen2-VL 72B Instruct
Alibaba
54
±1
local
~34GB
llama.cpp ›
372
Hermes 3 Llama 3.1 405B
Nous Research
54
±1
local
~114GB
131k
llama.cpp ›
373
Llama 3.1 70B Instruct
Meta
53
±0
api $0.72/M
+local
~27GB
128k
docs.aws.amazon.com ↗
+22
374
Gemma 3 27B
Google
53
±1
api $0.10/M
+local
~19GB
131k
deepinfra.com ↗
+23
375
Qwen2.5-VL 32B Instruct
Alibaba
53
±2
local
~23GB
33k
LM Studio ›
+1
376
GPT-4.1 nano
OpenAI
53
±1
api $0.17/M
1M
developers.openai.com ↗
+11
377
GLM-4 (0520)
Z.ai
53
±1
comparison only
378
Phi-4 14B
Microsoft
53
±1
api $0.087/M
+local
~10GB
16k
deepinfra.com ↗
+11
379
Bielik 11B v2.1 Instruct
SpeakLeash
53
±3
local
~8.5GB
llama.cpp ›
380
Qwen2.5-Math 7B Instruct
Alibaba
53
±2
†
local
~5.4GB
4k
LM Studio ›
381
Olmo 3 7B Think
Ai2
53
±1
local
~5.8GB
66k
LM Studio ›
382
s1.1 32B
Simple Scaling
53
±1
local
~22GB
33k
LM Studio ›
383
Ministral 3 8B
Mistral
53
±1
api $0.15/M
+local
~6.5GB
~68 tok/s
262k
docs.mistral.ai ↗
+3
384
Gemma 4 E4B
Google
53
±1
local
~6.4GB
~21 tok/s
131k
LM Studio ›
+8
385
Llama 3.1 Nemotron 70B Instruct
NVIDIA
53
±1
local
~43GB
128k
LM Studio ›
+4
386
Qwen3-VL 4B Instruct
Alibaba
53
±1
local
~4.4GB
256k
llama.cpp ›
387
GPT-4 (0613)
OpenAI
53
±1
api $37.50/M
8k
developers.openai.com ↗
+11
388
Nemotron-4 340B Instruct
NVIDIA
53
±2
comparison only
389
ERNIE 4.5 21B-A3B
Baidu
53
±1
comparison only
390
LFM2.5 2.6B
Liquid AI
53
±1
local
~2.3GB
131k
LM Studio ›
391
Bielik 11B v2.2 Instruct
SpeakLeash
53
±3
local
~8.5GB
llama.cpp ›
392
Llama 3.1 Nemotron 51B Instruct
NVIDIA
53
±2
local
~34GB
llama.cpp ›
393
Aya Expanse 32B
Cohere
53
±2
api $0.75/M
+local
~22GB
128k
docs.cohere.com ↗
+1
394
Palmyra X4 (palmyra-x-004)
Writer
53
±3
comparison only
395
Granite 4.0 H Small (32B-A9B)
IBM
53
±1
api $0.11/M
+local
~21GB
131k
replicate.com ↗
+1
396
Qwen2.5 Coder 7B Instruct
Alibaba
53
±1
local
~5.4GB
~3.8 tok/s
131k
LM Studio ›
397
OpenCoder-8B-Instruct
INF (infly)
53
±1
local
~6.4GB
llama.cpp ›
398
LFM2.5 8B-A1B
Liquid AI
52
±1
local
~5.5GB
~174 tok/s
128k
LM Studio ›
399
Gemma 3 12B
Google
52
±1
api $0.075/M
+local
~10GB
~13 tok/s
131k
deepinfra.com ↗
+10
400
Qwen2.5 14B Instruct
Alibaba
52
±1
local
~11GB
131k
LM Studio ›
+7
401
Yi-Large
01.AI
52
±1
comparison only
402
Cogito v1 Preview Llama 8B
Deep Cogito
52
±4
local
~6.2GB
128k
LM Studio ›
403
Llama-3-Instruct-8B-SimPO-ExPO
Chujie Zheng (ExPO)
52
±1
local
~6.6GB
llama.cpp ›
404
Llama-3-Instruct-8B-SimPO
Princeton NLP
52
±1
local
~6.6GB
llama.cpp ›
405
Athene-70B
Nexusflow
52
±1
local
~29GB
llama.cpp ›
406
Qwen2 72B Instruct
Alibaba
52
±1
local
~33GB
131k
llama.cpp ›
+14
407
Jamba 1.5 Large
AI21 Labs
52
±1
local
~839GB
how to run ›
408
Command A Translate (08-2025)
Cohere
52
±4
†
api price unknown
8k
docs.cohere.com ↗
409
CodeQwen1.5 7B Chat
Alibaba
52
±1
local
~6.4GB
64k
llama.cpp ›
410
OpenCodeInterpreter-DS-33B
M-A-P
51
±1
local
~22GB
LM Studio ›
411
Bielik 11B v2.0 Instruct
SpeakLeash
51
±3
local
~8.5GB
llama.cpp ›
412
Flan-U-PaLM 540B
Google
51
±1
†
never released
413
Gemini 1.5 Flash (001)
Google
51
±1
comparison only
+3
414
LFM2 24B-A2B
Liquid AI
51
±1
local
~14GB
33k
LM Studio ›
415
Qwen3 4B
Alibaba
51
±1
local
~4GB
33k
LM Studio ›
+8
416
DeepSeek-Coder 33B Instruct
DeepSeek
51
±1
local
~21GB
16k
LM Studio ›
+1
417
GLM-4 (0116)
Z.ai
51
±1
comparison only
418
Codestral 22B v0.1
Mistral AI
51
±1
local
~15GB
32k
LM Studio ›
419
Gemma 2 27B IT
Google
51
±1
local
~19GB
8k
LM Studio ›
+10
420
Llama 3 70B Instruct
Meta
51
±0
local
~24GB
8k
llama.cpp ›
+17
421
Llama 3.2 90B Vision Instruct
Meta
51
±1
local
~58GB
128k
Ollama ›
+1
422
WizardCoder 33B V1.1
WizardLM
51
±1
local
~22GB
16k
llama.cpp ›
423
Bielik 11B v2.3 Instruct
SpeakLeash
51
±2
local
~8.6GB
llama.cpp ›
424
Flan-PaLM 540B
Google
51
±1
†
never released
425
Llama-3-8B-ProLong-512k-Instruct
Princeton NLP
51
±4
local
~35GB
how to run ›
426
Nova Pro
Amazon
51
±1
api $1.40/M
300k
docs.aws.amazon.com ↗
427
OpenCodeInterpreter-DS-6.7B
M-A-P
51
±1
local
~5.8GB
llama.cpp ›
428
Qwen2-Math 72B Instruct
Alibaba
51
±1
local
~32GB
4k
llama.cpp ›
429
WizardLM-2 8x22B
Microsoft
51
±1
local
~91GB
Ollama ›
430
Mistral Small Instruct 22B (2409)
Mistral AI
51
±2
local
~15GB
32k
LM Studio ›
431
OpenThinker3 7B
Open Thoughts
51
±1
local
~6GB
33k
LM Studio ›
432
Granite 4.1 3B
IBM
51
±1
†
local
~3.7GB
~131 tok/s
Ollama ›
433
Artigenz-Coder-DS-6.7B
Artigenz
51
±1
local
~5.8GB
llama.cpp ›
434
Yi 34B 200K (base)
01.AI
51
±4
local
~23GB
200k
llama.cpp ›
435
Mellum2 12B-A2.5B Instruct
JetBrains
51
±2
†
local
~7.6GB
131k
LM Studio ›
436
Molmo 72B (0924)
Ai2
50
±2
local
~309GB
how to run ›
437
Hermes 3 Llama 3.1 70B
Nous Research
50
±1
local
~43GB
131k
Ollama ›
438
speechless-codellama-34b-v2.0
uukuguy
50
±1
local
~23GB
llama.cpp ›
439
OLMo 2 32B Instruct (0325)
Ai2
50
±1
local
~21GB
LM Studio ›
440
Ministral 3 3B Reasoning 2512
Mistral
50
±1
local
~3.4GB
262k
LM Studio ›
441
Aya 23 35B
Cohere For AI
50
±2
local
~22GB
8k
LM Studio ›
442
AceReason-Nemotron-1.0-14B
NVIDIA
50
±2
†
local
~10GB
LM Studio ›
443
Claude 3 Sonnet
Anthropic
50
±0
comparison only
+12
444
Qwen2.5-VL 7B Instruct
Alibaba
50
±1
local
~5.8GB
llama.cpp ›
445
Mixtral 8x22B Instruct v0.1
Mistral
50
±1
local
~56GB
64k
llama.cpp ›
+9
446
Magicoder-S-DS 6.7B
UIUC (ise-uiuc)
50
±1
local
~5.8GB
llama.cpp ›
447
EXAONE Deep 2.4B
LG AI Research
50
±2
†
local
~3.2GB
33k
Ollama ›
448
Pixtral 12B (2409)
Mistral
50
±2
local
~9.6GB
llama.cpp ›
449
Nova Lite
Amazon
50
±2
api $0.10/M
300k
docs.aws.amazon.com ↗
450
XwinCoder-34B
Xwin-LM
50
±1
local
~23GB
llama.cpp ›
451
Qwen2.5 7B Instruct
Alibaba
50
±1
api $0.30/M
+local
~5.4GB
~54 tok/s
131k
www.together.ai ↗
+12
452
LFM2.5 1.2B Thinking
Liquid AI
50
±2
local
~1.3GB
33k
LM Studio ›
453
Yi-Coder 9B Chat
01.AI
50
±1
local
~6.3GB
128k
LM Studio ›
454
InternLM2.5 7B Chat
Shanghai AI Laboratory (InternLM)
50
±2
local
~6.1GB
LM Studio ›
455
StarChat2 15B v0.1
Hugging Face
50
±1
local
~12GB
16k
llama.cpp ›
456
Code Millenials 34B
Bud Ecosystem
50
±1
local
~23GB
llama.cpp ›
457
Qwen2-Math 7B Instruct
Alibaba
50
±2
†
local
~6GB
4k
LM Studio ›
458
WaveCoder-Ultra-6.7B
Microsoft
50
±1
local
~5.8GB
llama.cpp ›
459
Reka Core (2024-05-01)
Reka AI
50
±1
comparison only
460
GPT-4o Audio Preview (2024-12-17)
OpenAI
49
±2
comparison only
461
MegaBeam-Mistral-7B-512k
AWS (aws-prototyping)
49
±4
local
~5.9GB
llama.cpp ›
462
Gemini 1.5 Flash-8B (001)
Google
49
±2
comparison only
463
Phi-3.5-MoE-instruct
Microsoft
49
±1
local
~25GB
128k
LM Studio ›
464
Qwen3-VL 2B Thinking
Alibaba
49
±1
local
~2.7GB
256k
llama.cpp ›
465
Gemma 3n E4B
Google
49
±1
local
~5.6GB
32k
llama.cpp ›
466
Claude 3 Haiku
Anthropic
49
±0
comparison only
+16
467
DeepSeek-Coder 7B Instruct v1.5
DeepSeek
49
±1
local
~5.9GB
llama.cpp ›
468
OpenThinker2 7B
Open Thoughts
49
±2
†
local
~6.4GB
33k
llama.cpp ›
469
DeepSeek-Coder 6.7B Instruct
DeepSeek
49
±1
local
~8.8GB
16k
llama.cpp ›
470
Qwen2 57B-A14B Instruct
Alibaba
49
±2
local
~35GB
33k
LM Studio ›
471
Hermes 2 Theta Llama-3 70B
Nous Research
49
±2
local
~47GB
8k
llama.cpp ›
472
MiniCPM3-4B
OpenBMB
49
±2
local
~4GB
32k
LM Studio ›
473
Granite 4.0 H Tiny (7B-A1B)
IBM
49
±1
local
~4.5GB
~12 tok/s
131k
LM Studio ›
474
Qwen2.5 Coder 3B Instruct
Alibaba
49
±1
local
~2.6GB
~9.5 tok/s
33k
LM Studio ›
475
Claude 1.3
Anthropic
49
±1
comparison only
+1
476
Gemma 2 9B IT
Google
49
±1
local
~8.9GB
8k
LM Studio ›
+14
477
Yi-1.5 34B (base)
01.AI
49
±2
local
~22GB
4k
LM Studio ›
478
Bielik 4.5B v3.0 Instruct
SpeakLeash
49
±2
local
~4.3GB
LM Studio ›
479
GPT-4o mini Audio Preview (2024-12-17)
OpenAI
49
±2
comparison only
480
WhiteRabbitNeo-33B-v1
WhiteRabbitNeo
49
±1
local
~22GB
llama.cpp ›
481
Qwen1.5 110B Chat
Alibaba
48
±1
local
~45GB
32k
llama.cpp ›
+1
482
Command R Plus (08-2024)
Cohere
48
±1
api $4.38/M
+local
~63GB
128k
docs.cohere.com ↗
+1
483
GLM-4 9B Chat
Zhipu AI (Z.ai)
48
±2
local
~7.1GB
128k
Ollama ›
+1
484
speechless-coder-ds-6.7b
uukuguy
48
±1
local
~5.8GB
llama.cpp ›
485
Magicoder-S-CL-7B
UIUC (ise-uiuc)
48
±1
local
~5.8GB
llama.cpp ›
486
Phind CodeLlama 34B v2
Phind
48
±1
local
~23GB
16k
Ollama ›
487
AceReason-Nemotron-1.1-7B
NVIDIA
48
±2
†
local
~6GB
LM Studio ›
488
Jamba 1.5 Mini
AI21 Labs
48
±1
local
~34GB
llama.cpp ›
489
DeepSeek R1 Distill Qwen 7B
DeepSeek
48
±1
local
~5.4GB
~35 tok/s
131k
LM Studio ›
+7
490
Mistral Large (2402)
Mistral
48
±1
comparison only
+3
491
U-PaLM 540B
Google
48
±1
†
never released
492
GPT-3.5 Turbo (0125)
OpenAI
48
±1
api $0.75/M
16k
developers.openai.com ↗
+11
493
InternVL2-26B
Shanghai AI Laboratory (OpenGVLab)
48
±2
local
~55GB
how to run ›
494
Aya Expanse 8B
Cohere
48
±2
local
~6.4GB
8k
LM Studio ›
495
EuroLLM 9B Instruct
UTTER (EuroLLM)
48
±2
local
~6.9GB
4k
LM Studio ›
496
Flan-UL2 20B
Google
48
±4
comparison only
497
GPT-3.5 Turbo (1106)
OpenAI
48
±1
comparison only
+2
498
Granite 4.0 H Micro 3B
IBM
48
±1
local
~3.4GB
131k
LM Studio ›
499
Minerva 540B
Google
48
±1
†
never released
500
Code Llama 70B Instruct
Meta
48
±1
local
~28GB
16k
llama.cpp ›
+1
501
Command R (08-2024)
Cohere
48
±1
api $0.26/M
+local
~21GB
128k
docs.cohere.com ↗
+3
502
OLMo 2 13B Instruct (1124)
Allen Institute for AI
48
±1
local
~9.6GB
4k
LM Studio ›
503
InternLM2.5 7B Chat 1M
Shanghai AI Laboratory (InternLM)
48
±4
local
~6.4GB
llama.cpp ›
504
Falcon-H1 7B Instruct
TII
48
±3
local
~6GB
262k
LM Studio ›
505
GPT-3.5 Turbo (0301)
OpenAI
47
±1
comparison only
+24
506
Llama 3 70B (base)
Meta
47
±2
local
~43GB
LM Studio ›
507
Nova Micro
Amazon
47
±2
api $0.061/M
128k
docs.aws.amazon.com ↗
508
Qwen3.5 2B
Alibaba
47
±1
local
~2.2GB
~137 tok/s
262k
llama.cpp ›
+7
509
Tulu 2 70B
Allen Institute for AI
47
±2
†
local
~28GB
llama.cpp ›
510
CogVLM2 Llama3 Chinese Chat 19B
Zhipu AI (THUDM)
47
±7
†
comparison only
511
Hermes 2 Pro Llama 3 8B
Nous Research
47
±3
local
~6.6GB
8k
llama.cpp ›
512
MedGemma 4B IT
Google
47
±2
local
~4.1GB
llama.cpp ›
513
Claude 2.0
Anthropic
47
±1
comparison only
+2
514
Yi 1.5 34B Chat
01.AI
47
±1
local
~22GB
4k
LM Studio ›
+5
515
OpenChat 3.5 0106
OpenChat
47
±1
local
~6.1GB
8k
llama.cpp ›
+1
516
GPT-3.5 Turbo (0613)
OpenAI
47
±1
comparison only
+5
517
WizardCoder Python 34B V1.0
WizardLM
47
±1
local
~22GB
16k
Ollama ›
518
Codex code-davinci-002 (GPT-3.5 base)
OpenAI
47
±0
comparison only
+20
519
Granite 4.0 Micro 3B
IBM
47
±1
local
~3.5GB
~6.2 tok/s
131k
LM Studio ›
520
Gemma 4 E2B
Google
47
±1
api $0.050/M
+local
~4.5GB
131k
docs.aws.amazon.com ↗
+6
521
Gemini 1.0 Pro (001)
Google
47
±2
comparison only
522
DBRX Instruct
Databricks
47
±1
local
~85GB
32k
Ollama ›
+3
523
Mistral Medium (2312)
Mistral
47
±1
comparison only
524
Granite 34B Code Instruct (8K)
IBM
47
±1
local
~22GB
Ollama ›
525
Cogito v1 Preview Llama 3B
Deep Cogito
47
±4
local
~3.4GB
128k
LM Studio ›
526
Qwen2.5-Math 1.5B Instruct
Alibaba
47
±2
†
local
~1.8GB
4k
LM Studio ›
527
EXAONE 4.0 1.2B
LG AI Research
47
±1
†
local
~2.2GB
66k
LM Studio ›
528
InternLM2.5 20B Chat
Shanghai AI Laboratory (InternLM)
47
±2
local
~14GB
33k
llama.cpp ›
529
StarCoder2-15B-Instruct-v0.1
BigCode
47
±1
local
~11GB
16k
Ollama ›
530
Flan-cont-PaLM 62B
Google
47
±1
†
never released
531
Qwen1.5 72B Chat
Alibaba
47
±1
local
~31GB
32k
llama.cpp ›
+9
532
Granite 3.3 8B Instruct
IBM
47
±1
local
~6.3GB
128k
LM Studio ›
533
speechless-starcoder2-15b
uukuguy
47
±1
local
~12GB
llama.cpp ›
534
OpenChat 3.5 0106 Gemma
OpenChat
47
±2
local
~6.9GB
8k
llama.cpp ›
535
Phi-3 Medium 128K Instruct
Microsoft
47
±1
local
~10GB
128k
LM Studio ›
536
Zephyr ORPO 141B-A35B v0.1
Hugging Face
47
±2
local
~56GB
66k
llama.cpp ›
537
Qwen2-VL 7B Instruct
Alibaba
47
±1
local
~5.8GB
LM Studio ›
538
LFM2 8B-A1B
Liquid AI
47
±1
comparison only
539
PaLM 540B
Google
47
±0
†
never released
+5
540
Claude 2.1
Anthropic
47
±1
comparison only
541
DeepSeek R1 Distill Llama 8B
DeepSeek
46
±1
local
~6.2GB
131k
LM Studio ›
+2
542
Phi-3-medium-4k-instruct
Microsoft
46
±1
local
~10GB
4k
LM Studio ›
+1
543
QwQ-32B-Preview
Alibaba
46
±2
local
~21GB
33k
LM Studio ›
+2
544
DeepSeek-Coder-V2 Lite Instruct (16B-A2.4B)
DeepSeek
46
±1
local
~9.6GB
128k
LM Studio ›
+1
545
Mistral Small (2402)
Mistral
46
±1
comparison only
546
Qwen2-Math 1.5B Instruct
Alibaba
46
±2
†
local
~2.4GB
4k
LM Studio ›
547
Minerva 62B
Google
46
±2
†
never released
548
Llama 3.1 8B Instruct
Meta
46
±0
api $0.22/M
+local
~6.2GB
~47 tok/s
128k
docs.aws.amazon.com ↗
+25
549
Phi-4-mini-reasoning 3.8B
Microsoft
46
±2
api $0.13/M
+local
~4GB
128k
azure.microsoft.com ↗
550
Ministral 3 3B
Mistral
46
±1
api $0.10/M
+local
~3.4GB
~128 tok/s
262k
docs.mistral.ai ↗
+2
551
Olmo 3 7B Instruct
Ai2
46
±1
local
~5.8GB
66k
LM Studio ›
552
GPT-3.5 text-davinci-003
OpenAI
46
±1
comparison only
+34
553
Command R Plus (04-2024)
Cohere
46
±1
local
~43GB
128k
llama.cpp ›
+6
554
Mistral NeMo Instruct (2407)
Mistral
46
±1
local
~8.8GB
128k
LM Studio ›
+9
555
GPT-4o Audio Preview (2024-10-01)
OpenAI
46
±2
comparison only
556
Llama 3.1 Tulu 3 8B
Ai2
46
±1
local
~6.2GB
131k
LM Studio ›
557
Phi-3-mini-4k-instruct (June 2024 update)
Microsoft
46
±1
local
~5.7GB
LM Studio ›
558
Yi 1.5 9B Chat
01.AI
46
±1
local
~6.8GB
4k
LM Studio ›
+1
559
Qwen1.5 32B Chat
Alibaba
46
±1
local
~22GB
32k
llama.cpp ›
560
Xwin-LM 70B v0.1
Xwin-LM
46
±1
local
~28GB
llama.cpp ›
561
Eurus-2-7B-PRIME
PRIME-RL
46
±2
local
~6.4GB
4k
llama.cpp ›
562
Qwen2 7B Instruct
Alibaba
46
±1
local
~5.4GB
131k
LM Studio ›
+4
563
Command R7B (12-2024)
Cohere
46
±1
local
~6.2GB
128k
LM Studio ›
564
Granite 20B Code Instruct (8K)
IBM
45
±1
local
~14GB
Ollama ›
565
Dolphin 2.6 Mixtral 8x7B
Cognitive Computations
45
±1
local
~29GB
llama.cpp ›
566
Gemma 3 4B
Google
45
±1
api $0.063/M
+local
~3.8GB
~74 tok/s
131k
deepinfra.com ↗
+11
567
Granite 3.0 8B Instruct
IBM
45
±1
local
~6.6GB
4k
llama.cpp ›
568
LLaVA-OneVision Qwen2 72B (ov-sft)
LLaVA (lmms-lab)
45
±3
local
~155GB
how to run ›
569
Granite 8B Code Instruct (4K)
IBM
45
±1
local
~6.6GB
llama.cpp ›
570
Falcon3 7B Instruct
TII
45
±2
local
~5.9GB
32k
LM Studio ›
571
Phi-4-mini 3.8B
Microsoft
45
±1
api $0.13/M
+local
~4GB
128k
azure.microsoft.com ↗
+4
572
Ministral 8B (2410)
Mistral
45
±1
local
~6.2GB
128k
LM Studio ›
+6
573
Code Llama 70B Python
Meta
45
±1
local
~28GB
16k
llama.cpp ›
574
Code Tulu 2 34B
Allen Institute for AI
45
±2
†
local
~72GB
how to run ›
575
Falcon3 10B Instruct
TII
45
±2
local
~7.6GB
~13 tok/s
32k
LM Studio ›
576
Granite 3.2 8B Instruct
IBM
45
±1
local
~6.6GB
131k
llama.cpp ›
577
OpenThinker 7B
Open Thoughts
45
±2
†
local
~6GB
33k
LM Studio ›
578
Yi 34B Chat
01.AI
45
±1
local
~23GB
4k
llama.cpp ›
+1
579
Hermes 2 Theta Llama 3 8B
Nous Research
45
±2
local
~6.6GB
8k
llama.cpp ›
580
Llama 3.1 8B (base)
Meta
45
±3
local
~6.2GB
LM Studio ›
581
Gemma 3n E2B IT
Google
45
±2
local
~4.1GB
32k
llama.cpp ›
582
Code Llama 70B (base)
Meta
45
±1
local
~28GB
16k
llama.cpp ›
583
Phi-3.5-mini-instruct
Microsoft
45
±1
local
~5.7GB
128k
LM Studio ›
+4
584
Qwen2.5-VL 3B Instruct
Alibaba
45
±1
local
~2.8GB
llama.cpp ›
585
Qwen3-VL 2B Instruct
Alibaba
45
±1
local
~2.7GB
256k
llama.cpp ›
586
LFM2.5 1.2B Instruct
Liquid AI
45
±2
local
~1.3GB
33k
LM Studio ›
587
Qwen3 1.7B
Alibaba
45
±1
local
~2.6GB
~96 tok/s
33k
LM Studio ›
+11
588
GPT-3.5 text-davinci-002
OpenAI
45
±0
comparison only
+22
589
Claude Instant 1.1
Anthropic
45
±2
comparison only
590
Granite 3.1 8B Instruct
IBM
44
±1
local
~6.7GB
128k
llama.cpp ›
591
Reka Flash 21B (2024-02-26)
Reka AI
44
±1
comparison only
592
Flan-PaLM 62B
Google
44
±1
†
never released
593
Llama 3.2 11B Vision Instruct
Meta
44
±2
local
~8.9GB
128k
Ollama ›
594
Qwen2.5 3B Instruct
Alibaba
44
±1
local
~2.6GB
~61 tok/s
33k
LM Studio ›
+5
595
LFM2 2.6B
Liquid AI
44
±1
local
~2GB
33k
LM Studio ›
596
CogVLM2 Llama3 Chat 19B
Zhipu AI (THUDM)
44
±3
local
~43GB
how to run ›
597
Tulu 2 DPO 70B
Ai2
44
±1
local
~32GB
llama.cpp ›
+1
598
Phi-3-small-8k-instruct
Microsoft
44
±2
local
~17GB
how to run ›
599
MiniCPM-V 2.6
OpenBMB
44
±2
local
~5.8GB
llama.cpp ›
600
CodeGemma 7B IT (v1.0)
Google
44
±1
local
~7.1GB
llama.cpp ›
601
Yi-1.5 9B (base)
01.AI
44
±2
local
~6.8GB
4k
LM Studio ›
602
Claude Instant 1.2
Anthropic
44
±1
comparison only
603
Qwen2-Audio 7B Instruct
Alibaba
44
±3
local
~6.5GB
llama.cpp ›
604
DeepSeek-Coder 1.3B Instruct
DeepSeek
44
±1
local
~2.9GB
16k
Ollama ›
605
Mathstral 7B v0.1
Mistral AI
44
±1
local
~5.6GB
32k
LM Studio ›
606
Aya 23 8B
Cohere For AI
44
±3
local
~6.2GB
8k
LM Studio ›
607
Qwen2.5 Coder 1.5B Instruct
Alibaba
44
±1
local
~1.8GB
33k
LM Studio ›
608
WizardLM 70B V1.0
Microsoft
44
±1
local
~32GB
llama.cpp ›
609
SmolLM3 3B
Hugging Face
44
±1
local
~2.9GB
66k
LM Studio ›
610
Hermes 3 Llama 3.1 8B
Nous Research
44
±1
local
~6.6GB
128k
llama.cpp ›
611
Llama 3 8B Instruct
Meta
44
±0
local
~6.6GB
8k
llama.cpp ›
+19
612
Command R (03-2024)
Cohere
44
±1
local
~33GB
128k
llama.cpp ›
+6
613
Aya Vision 32B
Cohere
44
±3
api price unknown
+local
~71GB
16k
docs.cohere.com ↗
614
WizardCoder Python 13B V1.0
WizardLM
43
±2
local
~15GB
16k
llama.cpp ›
615
OpenChat 3.5
OpenChat
43
±1
local
~6.1GB
8k
llama.cpp ›
616
Granite 34B Code Base (8K)
IBM
43
±1
local
~24GB
llama.cpp ›
617
speechless-starcoder2-7b
uukuguy
43
±1
local
~6.1GB
llama.cpp ›
618
OLMo 2 7B Instruct (1124)
Allen Institute for AI
43
±1
local
~5.8GB
4k
LM Studio ›
619
Falcon2 11B (base)
TII
43
±3
local
~8.2GB
8k
Ollama ›
620
Snowflake Arctic Instruct
Snowflake
43
±2
local
~1007GB
how to run ›
621
Phi-3-vision-128k-instruct
Microsoft
43
±2
local
~10GB
how to run ›
622
WizardCoder-15B-V1.0
WizardLM
43
±1
local
~12GB
llama.cpp ›
623
Ministral 3B (2410)
Mistral
43
±1
comparison only
624
cont-PaLM 62B (PaLM 62B trained to 1.3T tokens)
Google
43
±1
†
never released
625
DeepSeek LLM 67B Chat
DeepSeek
43
±1
local
~31GB
4k
llama.cpp ›
626
Qwen1.5 14B Chat
Alibaba
43
±1
local
~11GB
32k
Ollama ›
+3
627
Llama 2 70B (base)
Meta
43
±1
local
~32GB
4k
llama.cpp ›
628
Mixtral 8x7B v0.1 (base)
Mistral AI
43
±1
local
~29GB
32k
llama.cpp ›
629
Code Llama 34B Python
Meta
43
±1
local
~23GB
16k
Ollama ›
630
DeepSeek-Coder 33B Base
DeepSeek
43
±1
local
~22GB
16k
llama.cpp ›
631
speechless-coding-7b-16k-tora
uukuguy
43
±1
local
~16GB
how to run ›
632
InternVL2-4B
Shanghai AI Laboratory (OpenGVLab)
43
±2
local
~10GB
how to run ›
633
InternLM2 Chat 20B
Shanghai AI Laboratory (InternLM)
43
±1
local
~14GB
llama.cpp ›
634
CodeQwen1.5 7B (base)
Alibaba
42
±1
local
~6.4GB
66k
llama.cpp ›
635
Nous Hermes 2 Mistral 7B DPO
Nous Research
42
±3
local
~6.1GB
33k
llama.cpp ›
636
Mixtral 8x7B Instruct v0.1
Mistral
42
±0
local
~28GB
32k
LM Studio ›
+15
637
U-PaLM 62B
Google
42
±2
†
never released
638
Granite 4.0 1B
IBM
42
±1
local
~2.4GB
128k
LM Studio ›
639
OpenHermes-2.5-Code-290k-13B
ajibawa-2023
42
±1
local
~9.8GB
llama.cpp ›
640
Granite 4.0 H 1B
IBM
42
±1
local
~2.3GB
131k
LM Studio ›
641
Nous Hermes 2 Mixtral 8x7B DPO
Nous Research
42
±2
local
~30GB
33k
llama.cpp ›
642
Molmo 7B-D (0924)
Ai2
42
±1
local
~35GB
how to run ›
643
Deita 7B v1.0
HKUST NLP
42
±2
local
~32GB
how to run ›
644
Vicuna 13B v1.1
LMSYS
42
±2
comparison only
645
North Micro Vision Instruct (2.4B)
Cohere
42
±2
†
local
~3.8GB
128k
how to run ›
646
OpenHermes 2.5 Mistral 7B
Nous Research
42
±1
local
~5.9GB
llama.cpp ›
+2
647
Code Llama 34B Instruct
Meta
42
±1
local
~22GB
16k
LM Studio ›
+1
648
Code Llama 34B (base)
Meta
42
±1
local
~23GB
16k
Ollama ›
+1
649
Starling-LM 7B beta
Nexusflow
42
±1
local
~6GB
8k
LM Studio ›
+3
650
Vicuna 33B v1.3
LMSYS
41
±1
local
~23GB
2k
Ollama ›
+2
651
Phi-3-mini-128k-instruct (Apr 2024)
Microsoft
41
±2
local
~9.5GB
how to run ›
+1
652
Code Tulu 2 13B
Allen Institute for AI
41
±2
†
local
~29GB
how to run ›
653
Bielik 1.5B v3.0 Instruct
SpeakLeash
41
±3
local
~2.4GB
LM Studio ›
654
Starling-LM 7B alpha
UC Berkeley (NEST)
41
±1
local
~6.1GB
8k
llama.cpp ›
+2
655
Granite 3.3 2B Instruct
IBM
41
±1
†
local
~3GB
128k
LM Studio ›
656
Llama3-OpenBioLLM-8B
Saama AI Labs
41
±2
local
~6.6GB
llama.cpp ›
657
Mistral 7B Instruct v0.3
Mistral
41
±1
local
~5.6GB
32k
LM Studio ›
+4
658
LLaVA-v1.6-34B
LLaVA
41
±2
local
~24GB
4k
Ollama ›
659
LFM2 1.2B
Liquid AI
41
±1
local
~1.3GB
33k
LM Studio ›
660
DeepSeek-Coder 6.7B Base
DeepSeek
41
±1
local
~8.8GB
16k
llama.cpp ›
661
Granite 3.0 2B Instruct
IBM
41
±1
local
~3.2GB
4k
llama.cpp ›
662
Llama 2 70B Chat
Meta
41
±1
local
~32GB
4k
llama.cpp ›
+13
663
Llama 3.2 3B Instruct
Meta
41
±1
api $0.12/M
+local
~3.3GB
~139 tok/s
131k
developers.cloudflare.com ↗
+11
664
Granite 8B Code Base (4K)
IBM
41
±1
local
~6.6GB
llama.cpp ›
665
StarCoder2 15B
BigCode
41
±1
local
~11GB
16k
LM Studio ›
666
Llama-3-Instruct-8B-SimPO-v0.2
Princeton NLP
40
±1
local
~6.6GB
llama.cpp ›
667
Falcon-H1 3B Instruct
TII
40
±3
local
~3.4GB
131k
LM Studio ›
668
Phi-2 (2.7B)
Microsoft
40
±1
local
~4.7GB
2k
LM Studio ›
+2
669
speechless-code-mistral-7b-v1.0
uukuguy
40
±1
local
~17GB
how to run ›
670
Qwen-14B-Chat
Alibaba
40
±1
local
~11GB
llama.cpp ›
671
Code Llama 13B Instruct
Meta
40
±1
local
~15GB
16k
llama.cpp ›
672
Tulu 2 13B
Allen Institute for AI
40
±2
local
~9.8GB
llama.cpp ›
673
Falcon-180B-Chat
TII
40
±2
local
~115GB
2k
Ollama ›
674
MistralHermes-CodePro-7B-v1
beowolx
40
±1
local
~6.1GB
llama.cpp ›
675
LLaMA 65B
Meta
40
±1
comparison only
+7
676
Phi-3-mini-4k-instruct (Apr 2024)
Microsoft
40
±2
local
~6GB
llama.cpp ›
677
CodeGemma 7B (v1.0)
Google
40
±1
local
~7.1GB
llama.cpp ›
678
Code Llama 13B Python
Meta
40
±1
local
~9.8GB
16k
llama.cpp ›
679
Apertus 8B Instruct (2509)
Swiss AI
40
±3
local
~6.3GB
66k
LM Studio ›
680
DeepSeek-V2 Lite Chat (16B-A2.4B)
DeepSeek
40
±1
local
~11GB
32k
LM Studio ›
681
Granite 3B Code Instruct (2K)
IBM
40
±1
local
~3.7GB
llama.cpp ›
682
Tulu 2 DPO 13B
Allen Institute for AI
39
±1
local
~9.8GB
llama.cpp ›
683
PaLM 62B
Google
39
±1
†
never released
+4
684
BioMistral-7B
BioMistral
39
±3
local
~6.1GB
llama.cpp ›
685
SOLAR 10.7B Instruct v1.0
Upstage
39
±1
local
~8.3GB
4k
llama.cpp ›
+2
686
Gemma 2 2B IT
Google
39
±1
local
~3.2GB
8k
LM Studio ›
+4
687
Code Tulu 2 7B
Allen Institute for AI
39
±2
†
local
~16GB
how to run ›
688
Flan-T5 XXL
Google
39
±1
local
~49GB
how to run ›
+12
689
Yi-1.5 6B (base)
01.AI
39
±3
local
~5.1GB
4k
LM Studio ›
690
Dolphin 2.2.1 Mistral 7B
Cognitive Computations
39
±2
local
~5.9GB
llama.cpp ›
691
Gemma 1.1 7B IT
Google
39
±1
local
~7.1GB
8k
llama.cpp ›
+2
692
Granite 3.1 2B Instruct
IBM
39
±1
local
~3.1GB
128k
llama.cpp ›
693
Phi-3.5-vision-instruct
Microsoft
39
±2
local
~10GB
how to run ›
694
Granite 20B Code Base (8K)
IBM
39
±1
local
~15GB
llama.cpp ›
695
Code Llama 7B Python
Meta
39
±1
local
~5.8GB
16k
llama.cpp ›
696
Granite 3.2 2B Instruct
IBM
39
±1
local
~3GB
131k
LM Studio ›
697
Qwen1.5 7B Chat
Alibaba
39
±1
local
~9.7GB
32k
llama.cpp ›
+4
698
Zephyr 7B alpha
Hugging Face
38
±1
local
~6.1GB
llama.cpp ›
699
Code Llama 13B (base)
Meta
38
±1
local
~9.2GB
16k
LM Studio ›
+1
700
Falcon3 3B Instruct
TII
38
±3
local
~3.4GB
32k
LM Studio ›
701
Qwen2.5 Coder 0.5B Instruct
Alibaba
38
±1
local
~1GB
33k
LM Studio ›
702
Vicuna 13B v1.5
LMSYS
38
±1
local
~9.8GB
4k
llama.cpp ›
703
Yi 1.5 6B Chat
01.AI
38
±2
local
~4.4GB
4k
LM Studio ›
704
WizardLM 13B V1.2
Microsoft
38
±1
local
~9.8GB
llama.cpp ›
705
Qwen2-VL 2B Instruct
Alibaba
38
±1
local
~2.1GB
33k
LM Studio ›
706
Qwen2.5 1.5B Instruct
Alibaba
38
±1
local
~1.8GB
~98 tok/s
33k
LM Studio ›
+6
707
Tulu 2 7B
Allen Institute for AI
38
±2
local
~5.8GB
llama.cpp ›
708
MPT-30B-Chat
MosaicML
38
±2
comparison only
709
Mistral 7B Instruct v0.2
Mistral
38
±1
local
~5.8GB
32k
LM Studio ›
+9
710
Code Llama 7B Instruct
Meta
38
±1
local
~5.5GB
16k
LM Studio ›
711
LFM2 700M
Liquid AI
38
±1
local
~1GB
33k
LM Studio ›
712
Qwen3.5 0.8B
Alibaba
38
±1
local
~1.4GB
~94 tok/s
262k
llama.cpp ›
+2
713
LLaMA 33B
Meta
38
±1
comparison only
+9
714
EXAONE 3.5 2.4B Instruct
LG AI Research
38
±2
local
~3GB
33k
LM Studio ›
715
xDAN-L1-Chat-RL-v1
xDAN-AI
37
±1
local
~6.1GB
llama.cpp ›
716
Flan-PaLM 8B
Google
37
±1
†
never released
717
Mistral 7B v0.1 (base)
Mistral AI
37
±1
local
~5.8GB
8k
LM Studio ›
+4
718
Llama 3 8B (base)
Meta
37
±1
local
~6.6GB
llama.cpp ›
719
Flan-T5 XL
Google
37
±1
local
~14GB
how to run ›
+8
720
Gemma 7B (base)
Google
37
±1
local
~7.1GB
8k
llama.cpp ›
+3
721
Tulu 2 DPO 7B
Allen Institute for AI
37
±1
local
~5.8GB
llama.cpp ›
722
Vicuna 13B v1.3
LMSYS
37
±2
local
~29GB
2k
how to run ›
723
Granite 3.1 3B-A800M Instruct
IBM
37
±2
†
local
~3.6GB
~23 tok/s
131k
llama.cpp ›
724
Granite 3.0 3B-A800M Instruct
IBM
37
±1
local
~3.7GB
4k
llama.cpp ›
725
DeepSeek R1 Distill Qwen 1.5B
DeepSeek
37
±2
local
~1.9GB
131k
LM Studio ›
+1
726
StarCoder2 7B
BigCode
37
±1
local
~5.4GB
16k
LM Studio ›
727
Vicuna 7B v1.1
LMSYS
37
±2
comparison only
728
DeepSeek LLM 7B Chat
DeepSeek
37
±2
†
local
~5.7GB
Ollama ›
729
Falcon 40B (base)
TII
36
±1
local
~27GB
2k
Ollama ›
+2
730
StarCoder 15.5B
BigCode
36
±1
local
~11GB
Ollama ›
731
Nous-Hermes-13b
Nous Research
36
±2
local
~9.8GB
2k
llama.cpp ›
732
Eurus-2-7B-SFT
PRIME-RL
36
±3
†
local
~6.4GB
llama.cpp ›
733
Qwen3 0.6B
Alibaba
36
±1
local
~1.9GB
~182 tok/s
33k
LM Studio ›
+5
734
PaLM 2 Chat (chat-bison@001)
Google
36
±2
comparison only
735
Code Llama 7B (base)
Meta
36
±1
local
~5.5GB
16k
LM Studio ›
+2
736
Llama 2 13B (base)
Meta
36
±1
local
~9.3GB
4k
Ollama ›
+4
737
Llama 2 13B Chat
Meta
36
±1
local
~15GB
4k
llama.cpp ›
+10
738
Zephyr 7B beta
Hugging Face
35
±1
local
~6.1GB
llama.cpp ›
+3
739
Guanaco 33B
University of Washington
35
±1
local
~70GB
how to run ›
740
StarCoder2 3B
BigCode
35
±1
local
~3.4GB
16k
llama.cpp ›
741
Granite 3B Code Base (2K)
IBM
35
±1
local
~3.7GB
llama.cpp ›
742
StarCoderBase 15.5B
BigCode
35
±1
local
~12GB
llama.cpp ›
743
Vicuna 7B v1.5
LMSYS
35
±1
local
~5.8GB
4k
llama.cpp ›
+1
744
ChatGLM3 6B 128K
Zhipu AI (THUDM)
35
±4
local
~5.8GB
131k
llama.cpp ›
745
Minerva 8B
Google
35
±2
†
never released
746
OLMo 2 1B Instruct (0425)
Allen Institute for AI
35
±1
local
~2.4GB
4k
llama.cpp ›
747
Vicuna 7B v1.3
LMSYS
35
±2
local
~5.8GB
2k
llama.cpp ›
748
Stable Code 3B
Stability AI
35
±1
local
~4.8GB
16k
llama.cpp ›
749
Orca 2 13B
Microsoft
35
±3
local
~9.8GB
4k
llama.cpp ›
750
T0 11B
BigScience
35
±3
comparison only
751
DeepSeek-Coder 1.3B Base
DeepSeek
34
±1
local
~2.4GB
16k
Ollama ›
752
Qwen1.5 4B Chat
Alibaba
34
±2
local
~4.1GB
32k
llama.cpp ›
753
Mistral 7B Instruct v0.1
Mistral
34
±1
local
~5.9GB
8k
llama.cpp ›
+3
754
Gemma 7B IT
Google
34
±1
local
~7.1GB
8k
llama.cpp ›
+5
755
LaMDA 137B (pre-trained, LaMDA-PT)
Google
34
±1
†
never released
756
GPT-3 text-davinci-001
OpenAI
34
±1
comparison only
+5
757
CodeGemma 2B (v1.0)
Google
34
±1
local
~3.2GB
llama.cpp ›
758
Qwen2 1.5B Instruct
Alibaba
34
±1
local
~1.8GB
32k
LM Studio ›
+1
759
Falcon-H1 1.5B Instruct
TII
33
±4
local
~2.4GB
131k
LM Studio ›
760
Ghost 7B Alpha
Ghost X
33
±2
local
~6.1GB
llama.cpp ›
761
Gemma 3 1B
Google
33
±1
local
~1.7GB
~98 tok/s
32k
LM Studio ›
+7
762
SmolLM2 1.7B Instruct
Hugging Face
33
±1
local
~3GB
8k
LM Studio ›
763
LFM2 350M
Liquid AI
33
±1
local
~1.7GB
33k
LM Studio ›
764
Qwen-7B (base)
Alibaba
33
±1
local
~6.6GB
33k
llama.cpp ›
765
OPT-175B
Meta
33
±1
comparison only
766
BLOOMZ 176B
BigScience
33
±2
comparison only
767
StarCoderBase 7B
BigCode
33
±1
local
~6GB
Ollama ›
768
Codex code-davinci-001
OpenAI
33
±1
comparison only
769
Llama 3.2 1B Instruct
Meta
33
±1
api $0.020/M
+local
~1.6GB
~28 tok/s
131k
novita.ai ↗
+13
770
Phi-1.5 (1.3B)
Microsoft
33
±1
local
~2.4GB
2k
llama.cpp ›
771
LLaMA 13B
Meta
33
±1
comparison only
+19
772
Qwen-7B-Chat
Alibaba
32
±1
local
~6.6GB
33k
llama.cpp ›
773
Llama 2 7B Chat
Meta
32
±1
local
~8.8GB
4k
llama.cpp ›
+13
774
Koala 13B
UC Berkeley (BAIR)
32
±1
comparison only
+1
775
OLMo 7B Instruct
Ai2
32
±2
local
~16GB
how to run ›
776
Llama 2 7B (base)
Meta
32
±1
local
~8.5GB
4k
Ollama ›
+6
777
GPT-3 davinci (API base model)
OpenAI
32
±1
comparison only
+13
778
Flan-T5 Large
Google
32
±1
local
~4.8GB
how to run ›
+5
779
Granite 3.1 1B-A400M Instruct
IBM
31
±2
†
local
~2.3GB
~20 tok/s
131k
llama.cpp ›
780
Falcon 40B Instruct
TII
31
±2
local
~27GB
Ollama ›
781
Gemma 2B (base)
Google
31
±1
local
~3.2GB
8k
llama.cpp ›
+3
782
Gemma 1.1 2B IT
Google
31
±1
local
~3.2GB
8k
llama.cpp ›
+1
783
Falcon 7B (base)
TII
31
±1
local
~5.9GB
2k
Ollama ›
+4
784
Alpaca 7B
Stanford CRFM
31
±1
comparison only
785
Baichuan2-7B-Base
Baichuan
30
±1
local
~17GB
how to run ›
786
LLaMA 7B
Meta
30
±1
comparison only
+17
787
NexusRaven V2 13B
Nexusflow
30
±3
local
~9.3GB
16k
Ollama ›
788
MPT-7B (base)
MosaicML
30
±1
comparison only
789
ChatGLM3-6B
Zhipu AI (THUDM)
30
±2
local
~5.8GB
llama.cpp ›
790
Qwen2.5 0.5B Instruct
Alibaba
30
±2
local
~1GB
33k
LM Studio ›
+1
791
OLMo 7B
Allen Institute for AI
30
±1
†
local
~30GB
2k
how to run ›
792
OpenLLaMA 7B v2
OpenLM Research
30
±1
local
~9.1GB
llama.cpp ›
793
StableLM-3B-4E1T
Stability AI
30
±1
local
~3.3GB
4k
llama.cpp ›
794
StarCoderBase 3B
BigCode
30
±1
local
~3.4GB
Ollama ›
795
MPT-7B-Chat
MosaicML
30
±2
comparison only
796
StableLM-Base-Alpha 7B v2
Stability AI
30
±1
local
~30GB
4k
how to run ›
797
Granite 3.0 1B-A400M Instruct
IBM
30
±1
local
~2.3GB
4k
llama.cpp ›
798
OPT-66B
Meta
29
±1
local
~141GB
2k
how to run ›
+2
799
GPT4All-13B-Snoozy
Nomic AI
29
±2
local
~56GB
how to run ›
800
Alpaca 13B
Stanford CRFM
29
±2
comparison only
801
EuroLLM 1.7B Instruct
UTTER (EuroLLM)
29
±3
local
~2.4GB
4k
LM Studio ›
802
Granite 4.0 H 350M
IBM
29
±1
†
local
~1.7GB
33k
LM Studio ›
803
BLOOMZ 7.1B
BigScience
29
±2
comparison only
804
Gemma 2B IT
Google
29
±1
local
~3.1GB
8k
llama.cpp ›
+3
805
BLOOM 176B
BigScience
29
±1
local
~372GB
2k
how to run ›
+1
806
Granite 4.0 350M
IBM
28
±1
local
~1.7GB
32k
LM Studio ›
807
OPT-30B
Meta
28
±1
local
~64GB
2k
how to run ›
+5
808
UL2 20B
Google
28
±3
†
comparison only
809
GPT-NeoX-20B
EleutherAI
28
±1
local
~14GB
2k
LM Studio ›
+1
810
Qwen2 0.5B Instruct
Alibaba
28
±2
local
~1GB
32k
LM Studio ›
811
RedPajama-INCITE 7B Base
Together
28
±1
local
~16GB
2k
how to run ›
812
RWKV-4-Raven 14B
RWKV (BlinkDL)
28
±2
comparison only
813
ChatGLM2-6B
Zhipu AI (THUDM)
28
±2
local
~15GB
how to run ›
814
LaMDA 68B (pre-trained)
Google
27
±1
†
never released
815
BLOOMZ 3B
BigScience
27
±2
comparison only
816
Falcon3 1B Instruct
TII
26
±4
local
~2.4GB
8k
LM Studio ›
817
Qwen1.5 1.8B Chat
Alibaba
26
±2
local
~2.7GB
33k
Ollama ›
818
Tk-Instruct 11B (def)
AllenAI / UW
26
±4
comparison only
819
OPT-13B (13 billion parameters)
Meta
26
±1
local
~29GB
2k
how to run ›
+4
820
Falcon 7B Instruct
TII
26
±2
local
~5.9GB
Ollama ›
+1
821
PaLM 8B
Google
26
±1
†
never released
822
OpenAssistant SFT-4 Pythia 12B
LAION (OpenAssistant)
25
±1
local
~9.5GB
llama.cpp ›
+1
823
Flan-T5 Base
Google
25
±1
local
~2.5GB
how to run ›
+3
824
RedPajama-INCITE Base 3B v1
Together
25
±3
local
~3.4GB
2k
llama.cpp ›
825
GPT-3 curie (API base model)
OpenAI
25
±1
comparison only
+1
826
Pythia 12B
EleutherAI
25
±1
local
~9.5GB
2k
llama.cpp ›
+1
827
OpenLLaMA 3B v2
OpenLM Research
25
±1
local
~4.2GB
llama.cpp ›
828
GPT-J 6B
EleutherAI
25
±1
local
~14GB
2k
how to run ›
+6
829
ChatGLM-6B
Zhipu AI (THUDM)
25
±1
local
~16GB
how to run ›
+3
830
StableLM-Base-Alpha 3B v2
Stability AI
24
±1
local
~13GB
4k
how to run ›
831
OPT-6.7B
Meta
24
±1
local
~16GB
2k
how to run ›
+5
832
T0 3B
BigScience
23
±4
comparison only
833
BLOOMZ 1.7B
BigScience
23
±3
comparison only
834
Qwen1.5 0.5B Chat
Alibaba
23
±3
local
~1.7GB
33k
LM Studio ›
835
Pythia 6.9B
EleutherAI
23
±1
local
~6.1GB
2k
llama.cpp ›
+2
836
T0++ (T0pp) 11B
BigScience
23
±3
comparison only
837
Phi-1 (1.3B)
Microsoft
22
±4
local
~2.4GB
2k
llama.cpp ›
838
Dolly v2 12B
Databricks
22
±1
comparison only
+3
839
SmolLM2 360M Instruct
Hugging Face
22
±3
local
~1GB
8k
LM Studio ›
840
FastChat-T5 3B
LMSYS
21
±2
local
~8.5GB
how to run ›
841
OLMo 1B
Allen Institute for AI
21
±2
†
local
~2.2GB
2k
llama.cpp ›
842
BLOOM 7.1B
BigScience
21
±1
local
~7.1GB
2k
llama.cpp ›
+7
843
Pythia 2.8B
EleutherAI
20
±1
local
~3.4GB
2k
llama.cpp ›
844
Pythia 2.8B (deduped)
EleutherAI
20
±1
local
~3.4GB
2k
llama.cpp ›
845
Falcon-RW 1B
TII
20
±2
local
~4.3GB
2k
how to run ›
846
OPT-2.7B
Meta
19
±1
local
~7.1GB
2k
how to run ›
+3
847
StableLM-Tuned-Alpha 7B
Stability AI
18
±2
local
~6.9GB
llama.cpp ›
848
GPT-Neo 2.7B
EleutherAI
18
±1
local
~13GB
2k
how to run ›
+8
849
BLOOMZ 1.1B
BigScience
18
±3
comparison only
850
T5 Large
Google
17
±2
local
~4.6GB
1k
how to run ›
851
Gemma 3 270M IT
Google
17
±4
local
~1.1GB
32k
LM Studio ›
852
Flan-T5 Small
Google
16
±3
local
~1.8GB
how to run ›
853
BLOOM 3B
BigScience
16
±1
local
~4GB
2k
llama.cpp ›
+2
854
GPT-3 babbage (API base model)
OpenAI
16
±1
comparison only
855
BLOOMZ 560M
BigScience
15
±4
comparison only
856
OPT-1.3B
Meta
14
±1
local
~4.3GB
2k
how to run ›
+5
857
T5 Base
Google
14
±3
local
~2.4GB
1k
how to run ›
858
Pythia 1.4B
EleutherAI
14
±1
local
~2.4GB
2k
llama.cpp ›
859
Pythia 1B
EleutherAI
12
±1
local
~2.2GB
2k
llama.cpp ›
860
LaMDA 8B (pre-trained)
Google
12
±2
†
never released
861
GPT-3 text-curie-001
OpenAI
12
±1
comparison only
+3
862
GPT-Neo 1.3B
EleutherAI
12
±2
local
~7.1GB
2k
how to run ›
+3
863
T5 Small
Google
12
±3
local
~1.8GB
1k
how to run ›
864
BLOOM 1.7B
BigScience
11
±1
local
~3.1GB
2k
llama.cpp ›
+1
865
Zyte-1B
venkycs (aihub-app)
11
±2
local
~2.2GB
llama.cpp ›
866
LaMDA 2B (pre-trained)
Google
10
±2
†
never released
867
StableLM-Base-Alpha 7B
Stability AI
8
±1
local
~35GB
4k
how to run ›
868
Pythia 410M
EleutherAI
8
±2
local
~1.8GB
2k
llama.cpp ›
869
GPT-3 ada (API base model)
OpenAI
8
±1
comparison only
870
BLOOM 1.1B
BigScience
7
±1
local
~2.6GB
2k
llama.cpp ›
871
GPT-2 XL (1.5B)
OpenAI
7
±1
local
~2.8GB
~75 tok/s
1k
llama.cpp ›
+9
872
GPT-3 text-babbage-001
OpenAI
4
±2
comparison only
873
GPT-3 text-ada-001
OpenAI
1
±3
comparison only
874
OPT-350M
Meta
1
±1
local
~2.2GB
2k
how to run ›
+1
875
LaMDA 422M (pre-trained)
Google
1
±3
†
never released
876
StableLM-Base-Alpha 3B
Stability AI
1
±2
local
~17GB
4k
how to run ›
877
BLOOM 560M
BigScience
0
±1
local
~2.1GB
2k
llama.cpp ›
+1
878
Pythia 160M
EleutherAI
-2
±2
local
~1.6GB
2k
llama.cpp ›
879
GPT-2 Large (774M)
OpenAI
-3
±1
local
~2GB
~137 tok/s
1k
llama.cpp ›
+3
880
OPT-125M
Meta
-3
±1
local
~1.8GB
2k
how to run ›
+1
881
GPT-Neo 125M
EleutherAI
-3
±2
local
~2.1GB
2k
how to run ›
882
GPT-2 Medium (355M)
OpenAI
-5
±1
local
~1.8GB
1k
llama.cpp ›
+3
883
Pythia 70M
EleutherAI
-13
±2
local
~1.6GB
2k
llama.cpp ›
884
GPT-2 Small (124M)
OpenAI
-13
±2
local
~1.6GB
1k
LM Studio ›
+3
—
Grok Build 0.1
SpaceXAI (xAI)
no reviewed results
api $1.25/M
256k
docs.x.ai ↗
—
K2 Horizon 7B
Institute of Foundation Models (MBZUAI)
not scored yet
local
~8GB
524k
llama.cpp ›
—
LFM2.5 24B-A2B
Liquid AI
not yet calibrated
local
~17GB
131k
llama.cpp ›
—
LFM3 1.7B
Liquid AI
not yet calibrated
local
~2.6GB
262k
llama.cpp ›