Discover top AI models, tools, and insights.
| # | Model | Org | Score | Details |
|---|---|---|---|---|
| 🥇 |
Gemini-2.5-Pro
Google
|
100.0
|
📄 Proprietary
· 🚀 2025-03-25
|
|
| 🥈 |
Gemini-2.5-Pro-Preview-05-06
Google
|
98.0
|
📄 Proprietary
· 🚀 2025-03-25
|
|
| 🥉 |
ChatGPT-4o-latest (2025-03-26)
OpenAI
|
OpenAI |
94.4
|
📄 Proprietary
· 🚀 2024-08-08
|
| 4 |
GLM-4.5
Z.ai
|
Z.ai |
94.3
|
📄 MIT
|
| 5 |
Qwen3-235B-A22B-Instruct-2507
Alibaba
|
Alibaba |
93.2
|
📄 Apache 2.0
· 🚀 2025-07-21
|
| 6 |
DeepSeek-R1-0528
DeepSeek
|
DeepSeek |
93.2
|
📄 MIT
· 🚀 2025-05-28
|
| 7 |
Grok-3-Preview-02-24
xAI
|
xAI |
92.5
|
📄 Proprietary
· 🚀 2025-02-17
|
| 8 |
Grok-4-0709
xAI
|
xAI |
92.2
|
📄 Proprietary
· 🚀 2025-11-01
|
| 9 |
o3-2025-04-16
OpenAI
|
OpenAI |
91.6
|
📄 Proprietary
· 🚀 2025-04-16
|
| 10 |
Llama-4-Maverick-03-26-Experimental
Meta
|
Meta |
91.4
|
· 🚀 2025-04-05
|
| 11 |
Gemini-2.5-Flash
Google
|
91.2
|
📄 Proprietary
· 🚀 2025-04-17
|
|
| 12 |
Qwen3-235B-A22B-Thinking-2507
Alibaba
|
Alibaba |
91.0
|
📄 Apache 2.0
· 🚀 2025-07-25
|
| 13 |
chocolate (Early Grok-3)
xAI
|
xAI |
90.8
|
📄 Proprietary
|
| 14 |
Gemini-Exp-1121
Google
|
88.9
|
📄 Proprietary
|
|
| 15 |
gemini-2.5-pro-exp-03-25
Google
|
88.9
|
· 🚀 2025-03-25
|
|
| 16 |
GLM-4.5-Air
Z.ai
|
Z.ai |
87.8
|
📄 MIT
|
| 17 |
calme-2.1-qwen2.5-72b
MaziyarPanahi
|
MaziyarPanahi |
87.7
|
📐 72.7B
·
📄 other
|
| 18 |
ChatGPT-4o-latest (2025-01-29)
OpenAI
|
OpenAI |
87.7
|
📄 Proprietary
· 🚀 2024-08-08
|
| 19 |
Gemini-2.0-Flash-Thinking-Exp-01-21
Google
|
87.7
|
📄 Proprietary
· 🚀 2025-02-05
|
|
| 20 |
Qwen2.5-72B-Instruct-abliterated
huihui-ai
|
huihui-ai |
87.6
|
📐 72.706B
·
📄 other
|
| 21 |
Qwen3-235B-A22B-no-thinking
Alibaba
|
Alibaba |
87.5
|
📄 Apache 2.0
|
| 22 |
Gemini-2.5-Flash-Preview-04-17
Google
|
87.2
|
📄 Proprietary
· 🚀 2025-04-17
|
|
| 23 |
GPT-4.5-Preview
OpenAI
|
OpenAI |
87.0
|
📄 Proprietary
· 🚀 2025-02-27
|
| 24 |
calme-2.2-qwen2.5-72b
MaziyarPanahi
|
MaziyarPanahi |
86.9
|
📐 72.7B
·
📄 other
|
| 25 |
GPT-4.1-2025-04-14
OpenAI
|
OpenAI |
85.9
|
📄 Proprietary
· 🚀 2025-04-14
|
| 26 |
Qwen2.5-32B-Instruct
Alibaba
|
Alibaba |
85.7
|
📐 32.764B
·
📄 apache-2.0
· 🚀 2024-09-17
|
| 27 |
kimi-k2-0711-preview
Moonshot AI
|
Moonshot AI |
85.7
|
📄 Modified MIT
· 🚀 2025-07-01
|
| 28 |
Qwen3-30B-A3B-Instruct-2507
Alibaba
|
Alibaba |
85.7
|
📄 Apache 2.0
· 🚀 2025-07-28
|
| 29 |
Awqward2.5-32B-Instruct
maldv
|
maldv |
85.7
|
📐 32.764B
·
📄 apache-2.0
|
| 30 |
claude-3-7-sonnet-20250219-thinking-64k
Anthropic
|
Anthropic |
85.2
|
|
| 31 |
Linkbricks-Horizon-AI-Avengers-V3-32B
Saxo
|
Saxo |
85.1
|
📐 32.764B
·
📄 apache-2.0
|
| 32 |
Gemini-2.0-Flash-Thinking-Exp-1219
Google
|
85.1
|
📄 Proprietary
· 🚀 2025-02-05
|
|
| 33 |
Hunyuan-Turbos-20250416
Tencent
|
Tencent |
85.1
|
📄 Proprietary
|
| 34 |
DeepSeek-V3-0324
DeepSeek
|
DeepSeek |
85.1
|
📄 MIT
· 🚀 2025-03-24
|
| 35 |
Linkbricks-Horizon-AI-Avengers-V6-32B
Saxo
|
Saxo |
85.0
|
📐 32.76B
·
📄 apache-2.0
|
| 36 |
Gemini-Exp-1114
Google
|
84.8
|
📄 Proprietary
|
|
| 37 |
Qwen2.5-32B-Instruct-abliterated-v2
zetasepic
|
zetasepic |
84.8
|
📐 32.764B
·
📄 apache-2.0
|
| 38 |
Linkbricks-Horizon-AI-Avengers-V1-32B
Saxo
|
Saxo |
84.6
|
📐 32.76B
·
📄 apache-2.0
|
| 39 |
zetasepic-abliteratedV2-Qwen2.5-32B-Inst-BaseMerge-TIES
CombinHorizon
|
CombinHorizon |
84.5
|
📐 32.764B
·
📄 apache-2.0
|
| 40 |
DeepSeek-R1
DeepSeek
|
DeepSeek |
84.4
|
📄 MIT
· 🚀 2025-01-20
|
| 41 |
qwen2.5-test-32b-it
ehristoforu
|
ehristoforu |
84.4
|
📐 32.764B
|
| 42 |
Gemini-Exp-1206
Google
|
83.7
|
📄 Proprietary
|
|
| 43 |
huihui-ai-abliterated-Qwen2.5-32B-Inst-BaseMerge-TIES
CombinHorizon
|
CombinHorizon |
83.6
|
📐 32.764B
·
📄 apache-2.0
|
| 44 |
Gemini-2.0-Flash-Exp
Google
|
83.6
|
📄 Proprietary
· 🚀 2025-02-05
|
|
| 45 |
Qwen2.5-Max
Alibaba
|
Alibaba |
83.5
|
📄 Proprietary
|
| 46 |
lambda-qwen2.5-32b-dpo-test
tanliboy
|
tanliboy |
83.5
|
📐 32.764B
·
📄 apache-2.0
|
| 47 |
Gemini-2.0-Pro-Exp-02-05
Google
|
83.4
|
📄 Proprietary
· 🚀 2025-02-05
|
|
| 48 |
Qwen3-235B-A22B
Alibaba
|
Alibaba |
83.3
|
📄 Apache 2.0
· 🚀 2025-04-27
|
| 49 |
FluentlyLM-Prinum
fluently-lm
|
fluently-lm |
83.3
|
📐 32.764B
·
📄 mit
|
| 50 |
Qwen2.5-72B-Instruct
Alibaba
|
Alibaba |
83.2
|
📐 72.706B
·
📄 Qwen
· 📅 2024/9
· 🚀 2024-09-16
|
| 51 |
o4-mini-2025-04-16
OpenAI
|
OpenAI |
82.8
|
📄 Proprietary
· 🚀 2025-04-16
|
| 52 |
Grok-3-mini-high
xAI
|
xAI |
82.7
|
📄 Proprietary
· 🚀 2025-02-17
|
| 53 |
Qwen2.5-95B-Instruct
ssmits
|
ssmits |
82.7
|
📐 94.648B
·
📄 other
|
| 54 |
Grok-3-Mini-beta
xAI
|
xAI |
82.5
|
📄 Proprietary
· 🚀 2025-02-17
|
| 55 |
claude-3-7-sonnet-20250219-thinking-25k
Anthropic
|
Anthropic |
82.4
|
|
| 56 |
ChatGPT-4o-latest (2024-09-03)
OpenAI
|
OpenAI |
82.1
|
📄 Proprietary
· 📅 2023/10
· 🚀 2024-08-08
|
| 57 |
Qwen3-Coder-480B-A35B-Instruct
Alibaba
|
Alibaba |
82.1
|
📄 Apache 2.0
· 🚀 2025-07-22
|
| 58 |
o1-2024-12-17-high
OpenAI
|
OpenAI |
82.0
|
· 🚀 2024-12-17
|
| 59 |
o1-preview-2024-09-12
OpenAI
|
OpenAI |
82.0
|
· 🚀 2024-09-12
|
| 60 |
shuttle-3
shuttleai
|
shuttleai |
81.9
|
📐 72.706B
·
📄 other
|
| 61 |
Claude Opus 4 (thinking-16k)
Anthropic
|
Anthropic |
81.9
|
📄 Proprietary
· 🚀 2025-05-22
|
| 62 |
calme-3.2-instruct-78b
MaziyarPanahi
|
MaziyarPanahi |
81.8
|
📐 77.965B
·
📄 other
|
| 63 |
Minimax-M1
MiniMax
|
MiniMax |
81.6
|
📄 Apache 2.0
· 🚀 2025-05-29
|
| 64 |
CalmeRys-78B-Orpo-v0.1
dfurman
|
dfurman |
81.6
|
📐 77.965B
·
📄 mit
|
| 65 |
Linkbricks-Horizon-AI-Avengers-V2-32B
Saxo
|
Saxo |
81.5
|
📐 32.76B
·
📄 apache-2.0
|
| 66 |
o1-preview
OpenAI
|
OpenAI |
81.4
|
📄 Proprietary
· 📅 2023/10
· 🚀 2024-09-12
|
| 67 |
Gilgamesh-72B
rubenroy
|
rubenroy |
81.4
|
📐 72.706B
·
📄 other
|
| 68 |
BigQwen2.5-52B-Instruct
mlabonne
|
mlabonne |
81.4
|
📐 52.268B
·
📄 apache-2.0
|
| 69 |
Homer-v1.0-Qwen2.5-72B
newsbang
|
newsbang |
81.3
|
📐 72.706B
·
📄 apache-2.0
|
| 70 |
ChatGPT-4o-latest (2024-11-20)
OpenAI
|
OpenAI |
81.2
|
📄 Proprietary
· 🚀 2024-08-08
|
| 71 |
calme-3.1-instruct-78b
MaziyarPanahi
|
MaziyarPanahi |
81.2
|
📐 77.965B
·
📄 other
|
| 72 |
calme-2.4-rys-78b
MaziyarPanahi
|
MaziyarPanahi |
81.0
|
📐 77.965B
·
📄 mit
|
| 73 |
Rombos-LLM-V2.5-Qwen-72b
rombodawg
|
rombodawg |
81.0
|
📐 72.706B
·
📄 other
|
| 74 |
o3-mini-2025-01-31-high
OpenAI
|
OpenAI |
80.9
|
· 🚀 2025-01-31
|
| 75 |
ultiima-72B
Sakalti
|
Sakalti |
80.8
|
📐 72.706B
·
📄 other
|
| 76 |
o1-2024-12-17
OpenAI
|
OpenAI |
80.5
|
📄 Proprietary
· 🚀 2024-12-17
|
| 77 |
test-2.5-72B
raphgg
|
raphgg |
80.4
|
📐 72.706B
·
📄 apache-2.0
|
| 78 |
Linkbricks-Horizon-AI-Avengers-V5-32B
Saxo
|
Saxo |
80.2
|
📐 32.764B
·
📄 apache-2.0
|
| 79 |
Claude Sonnet 4 (thinking-32k)
Anthropic
|
Anthropic |
80.2
|
📄 Proprietary
· 🚀 2025-05-22
|
| 80 |
Claude Opus 4 (20250514)
Anthropic
|
Anthropic |
80.2
|
📄 Proprietary
· 🚀 2025-05-22
|
| 81 |
Linkbricks-Horizon-AI-Avengers-V4-32B
Saxo
|
Saxo |
80.1
|
📐 32.764B
·
📄 apache-2.0
|
| 82 |
Mistral-Large-Instruct-2411
Mistral AI
|
Mistral AI |
80.0
|
📐 122.61B
·
📄 other
· 🚀 2024-11-14
|
| 83 |
sky-t1-coder-32b-flash
tomasmcm
|
tomasmcm |
80.0
|
📐 32.764B
·
📄 apache-2.0
|
| 84 |
deepseek-r1-local
DeepSeek
|
DeepSeek |
79.7
|
· 🚀 2025-01-20
|
| 85 |
GPT-4.1-mini-2025-04-14
OpenAI
|
OpenAI |
79.7
|
📄 Proprietary
· 🚀 2025-04-14
|
| 86 |
Gemma-3-27B-it
Google
|
79.5
|
📄 Gemma
· 🚀 2025-03-01
|
|
| 87 |
Qwen3-32B
Alibaba
|
Alibaba |
79.5
|
📄 Apache 2.0
· 🚀 2025-04-27
|
| 88 |
Qwentile2.5-32B-Instruct
maldv
|
maldv |
79.3
|
📐 32.764B
·
📄 apache-2.0
|
| 89 |
li-14b-v0.4
wanlige
|
wanlige |
79.3
|
📐 14.77B
|
| 90 |
Nvidia-Llama-3.3-Nemotron-Super-49B-v1.5
NVIDIA
|
NVIDIA |
79.2
|
📄 Nvidia Open
|
| 91 |
tempmotacilla-cinerea-0308
Cran-May
|
Cran-May |
79.2
|
📐 14.766B
|
| 92 |
o3-mini-high
OpenAI
|
OpenAI |
79.0
|
📄 Proprietary
· 🚀 2025-01-31
|
| 93 |
ZYH-LLM-Qwen2.5-14B-V4
YOYO-AI
|
YOYO-AI |
79.0
|
📐 14.766B
·
📄 apache-2.0
|
| 94 |
Cheng-2
marcuscedricridia
|
marcuscedricridia |
78.9
|
📐 14.766B
|
| 95 |
Gemini-2.0-Flash-001
Google
|
78.7
|
📄 Proprietary
· 🚀 2025-02-05
|
|
| 96 |
Mistral Medium 3
Mistral AI
|
Mistral AI |
78.6
|
📄 Proprietary
|
| 97 |
Gemma-3-12B-it
Google
|
78.6
|
📄 Gemma
· 🚀 2025-03-01
|
|
| 98 |
Llama-3.3-70B-Instruct
Meta
|
Meta |
78.6
|
📐 70.554B
·
📄 Llama-3.3
· 🚀 2024-11-26
|
| 99 |
deepseek-r1-local-2
DeepSeek
|
DeepSeek |
78.5
|
· 🚀 2025-01-20
|
| 100 |
Cheng-2-v1.1
marcuscedricridia
|
marcuscedricridia |
78.5
|
📐 14.766B
|
Sources: LMSYS Chatbot Arena · HuggingFace Open LLM · LiveBench (Updated Daily)