Skip to content
IFAI

Model rankings

451 models · 2 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated July 28, 2025

Smartest
Grok 4xAI73.2Intelligence
Best open model
Qwen3 235B A22B 2507 (Reasoning)Alibaba68.9Intelligence
Best value
Gemma 3n E4B InstructGoogle1,120 pts/$Value
Best from China
Qwen3 235B A22B 2507 (Reasoning)Alibaba68.9Intelligence
Top three by Intelligence
1Grok 4xAI73.2
2o3-proOpenAI71.0
3Gemini 2.5 ProGoogle70.5
Top three open models
1Qwen3 235B A22B 2507 (Reasoning)Alibaba · #6 overall68.9
2DeepSeek R1 0528 (May '25)DeepSeek · #8 overall68.3
3MiniMax M1 80kMiniMax · #13 overall63.0
This week's changes
Qwen3 Coder 480B A35BIntelligence · #32New
Granite 3.3 Instruct 8BIntelligence · #130New
Gemma 3n E2B InstructIntelligence · #144New
Qwen3 235B A22B 2507 (Reasoning)Intelligence · #6Up 8
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1NewQwen3 235B A22B 2507 (Reasoning)OpenAlibaba68.9$2.6——
2▼ 1DeepSeek R1 0528 (May '25)OpenDeepSeek68.3$0.96——
3▼ 1MiniMax M1 80kOpenMiniMax63.0$0.83——
4▼ 1Qwen3 235B A22B (Reasoning)OpenAlibaba62.3$2.6——
5▼ 1MiniMax M1 40kOpenMiniMax61.4$0.83——
6▼ 1Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA60.8$0.90——
7NewQwen3 235B A22B 2507 (Non-reasoning)OpenAlibaba60.4$1.2——
8▼ 2DeepSeek R1 (Jan '25)OpenDeepSeek60.2$1.8——
9▼ 2Qwen3 32B (Reasoning)OpenAlibaba59.2$2.6——
10▼ 2QwQ 32BOpenAlibaba58.1$0.47——
11▼ 2Kimi K2OpenMoonshot AI57.6$1.1——
12▼ 2Qwen3 14B (Reasoning)OpenAlibaba55.7$1.3——
13▼ 2Qwen3 30B A3B (Reasoning)OpenAlibaba55.6$0.75——
14▼ 2Magistral SmallOpenMistral54.7$0.75——
15NewQwen3 Coder 480B A35BOpenAlibaba53.7$3.0——
16▼ 3DeepSeek V3 0324 (Mar '25)OpenDeepSeek53.2$0.48——
17▼ 3DeepSeek R1 0528 Qwen3 8BOpenDeepSeek52.2$0.065——
18▼ 3DeepSeek R1 Distill Qwen 32BOpenDeepSeek51.9$0.30——
19▼ 3Qwen3 8B (Reasoning)OpenAlibaba51.4$0.66——
20▼ 3Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA51.2$0.000——
21▼ 3Llama 4 MaverickOpenMeta50.5$0.39——
22▼ 3DeepSeek R1 Distill Qwen 14BOpenDeepSeek49.0$0.20——
23▼ 3DeepSeek R1 Distill Llama 70BOpenDeepSeek48.2$0.72——
24▼ 3Qwen3 4B (Reasoning)OpenAlibaba47.3$0.40——
25▼ 3Reka Flash 3OpenReka AI47.1$0.35——
26▼ 3Qwen3 235B A22BOpenAlibaba47.1$1.2——
27▼ 3DeepSeek V3 (Dec '24)OpenDeepSeek45.6$0.48——
28▼ 3Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA45.0$0.000——
29▼ 3Qwen3 32BOpenAlibaba43.5$1.2——
30▼ 3Llama 4 ScoutOpenMeta43.0$0.23——
31▼ 3QwQ 32B-PreviewOpenAlibaba42.6$0.67——
32▼ 3Qwen3 30B A3BOpenAlibaba42.6$0.35——
33▼ 3Mistral Small 3.2OpenMistral42.3$0.15——
34▼ 3Llama 3.3 Instruct 70BOpenMeta41.1$0.60——
35▼ 3Qwen3 14BOpenAlibaba41.0$0.61——
36▼ 3Llama 3.1 Instruct 405BOpenMeta40.5$3.3——
37▼ 3Qwen2.5 Instruct 72BOpenAlibaba40.4$0.000——
38▼ 3MiniMax-Text-01OpenMiniMax40.2$0.43——
39▼ 3Phi-4OpenMicrosoft Azure40.2$0.22——
40▼ 3Command AOpenCohere40.0$4.4——
41▼ 3Llama 3.1 Tulu3 405BOpenAllen Institute for AI39.9$0.000——
42▼ 3Llama 3.3 Nemotron Super 49B v1OpenNVIDIA39.3$0.000——
43▼ 3Mistral Large 2 (Nov '24)OpenMistral38.3$3.0——
44▼ 3Qwen3 1.7B (Reasoning)OpenAlibaba38.2$0.40——
45▼ 3Gemma 3 27B InstructOpenGoogle37.6$0.000——
46▼ 3Pixtral LargeOpenMistral37.4$3.0——
47▼ 3Qwen2.5 Instruct 32BOpenAlibaba37.4$0.15——
48▼ 3Llama 3.1 Nemotron Instruct 70BOpenNVIDIA37.3$0.16——
49▼ 3Qwen3 8BOpenAlibaba36.7$0.31——
50▼ 3Mistral Large 2 (Jul '24)OpenMistral36.6$3.0——

Intelligence over time

Each maker's best model at the time on the Artificial Analysis Intelligence Index, by the month it was released.

Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi

Arena data comes from the leaderboard dataset it publishes on Hugging Face (CC BY 4.0). Only each board's overall leaderboard is used; scores and ranks are unchanged. dataset · CC BY 4.0

Artificial Analysis data comes from its API (artificialanalysis.ai). Scores are unchanged; ranks follow the scores. artificialanalysis.ai

Open or closed follows the license Arena gives; prices and Artificial Analysis intelligence show only where model names match, otherwise “—”.