Skip to content
IFAI

Model rankings

394 models · 2 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated June 3, 2025

Smartest
o3OpenAI70.0Intelligence
Best open model
DeepSeek R1 0528 (May '25)DeepSeek68.3Intelligence
Best value
Gemma 3 4B InstructGoogle979 pts/$Value
Best from China
DeepSeek R1 0528 (May '25)DeepSeek68.3Intelligence
Top three by Intelligence
1o3OpenAI70.0
2o4-mini (high)OpenAI69.8
Top three open models
1DeepSeek R1 0528 (May '25)DeepSeek · #4 overall68.3
2Qwen3 235B A22B (Reasoning)Alibaba · #9 overall62.3
This week's changes
DeepSeek R1 0528 (May '25)Intelligence · #4Up 7
Claude 4 Opus (Extended Thinking)Intelligence · #8Up 6
o3Intelligence · #1Up 2
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1NewDeepSeek R1 0528 (May '25)OpenDeepSeek68.3$0.96——
2▼ 1Qwen3 235B A22B (Reasoning)OpenAlibaba62.3$2.6——
3▼ 1Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA60.8$0.90——
4NewDeepSeek R1 (Jan '25)OpenDeepSeek60.2$2.6——
5▼ 1Qwen3 32B (Reasoning)OpenAlibaba59.2$2.6——
6▼ 1QwQ 32BOpenAlibaba58.1$0.54——
7▼ 1Qwen3 14B (Reasoning)OpenAlibaba55.7$1.3——
8▼ 1Qwen3 30B A3B (Reasoning)OpenAlibaba55.6$0.75——
9NewDeepSeek V3 0324 (Mar '25)OpenDeepSeek53.2$0.48——
10▼ 1DeepSeek R1 Distill Qwen 32BOpenDeepSeek51.9$0.22——
11▼ 1Qwen3 8B (Reasoning)OpenAlibaba51.4$0.66——
12▼ 1Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA51.2$0.000——
13▼ 1Llama 4 MaverickOpenMeta50.5$0.37——
14▼ 1DeepSeek R1 Distill Qwen 14BOpenDeepSeek49.0$0.88——
15▼ 1DeepSeek R1 Distill Llama 70BOpenDeepSeek48.2$0.77——
16▼ 1Qwen3 4B (Reasoning)OpenAlibaba47.3$0.40——
17▼ 1Reka Flash 3OpenReka AI47.1$0.35——
18▼ 1Qwen3 235B A22BOpenAlibaba47.1$1.2——
19▼ 1DeepSeek V3 (Dec '24)OpenDeepSeek45.6$0.48——
20▼ 1Qwen3 32BOpenAlibaba43.5$1.2——
21▼ 1Llama 4 ScoutOpenMeta43.0$0.26——
22▼ 1QwQ 32B-PreviewOpenAlibaba42.6$0.20——
23▼ 1Qwen3 30B A3BOpenAlibaba42.6$0.35——
24▼ 1Llama 3.3 Instruct 70BOpenMeta41.1$0.62——
25▼ 1Qwen3 14BOpenAlibaba41.0$0.61——
26▼ 1Llama 3.1 Instruct 405BOpenMeta40.5$3.5——
27▼ 1Qwen2.5 Instruct 72BOpenAlibaba40.4$0.000——
28▼ 1MiniMax-Text-01OpenMiniMax40.2$0.43——
29▼ 1Phi-4OpenMicrosoft Azure40.2$0.22——
30▼ 1Command AOpenCohere40.0$4.4——
31▼ 1Llama 3.1 Tulu3 405BOpenAllen Institute for AI39.9$0.000——
32▼ 1Llama 3.3 Nemotron Super 49B v1OpenNVIDIA39.3$0.000——
33▼ 1Mistral Large 2 (Nov '24)OpenMistral38.3$3.0——
34▼ 1Qwen3 1.7B (Reasoning)OpenAlibaba38.2$0.40——
35▼ 1Gemma 3 27B InstructOpenGoogle37.6$0.000——
36▼ 1Pixtral LargeOpenMistral37.4$3.0——
37▼ 1Qwen2.5 Instruct 32BOpenAlibaba37.4$0.15——
38▼ 1Llama 3.1 Nemotron Instruct 70BOpenNVIDIA37.3$0.16——
39▼ 1Qwen3 8BOpenAlibaba36.7$0.31——
40▼ 1Mistral Large 2 (Jul '24)OpenMistral36.6$3.0——
41▼ 1Qwen2.5 Coder Instruct 32BOpenAlibaba36.3$0.15——
42▼ 1Llama 3.1 Instruct 70BOpenMeta35.4$0.72——
43▼ 1Mistral Small 3.1OpenMistral35.3$0.15——
44▼ 1Mistral Small 3OpenMistral35.3$0.15——
45▼ 1DeepSeek-V2.5 (Dec '24)OpenDeepSeek35.3$0.18——
46▼ 1Qwen3 4BOpenAlibaba35.2$0.19——
47▼ 1DeepSeek-V2.5OpenDeepSeek34.7$0.18——
48▼ 1DevstralOpenMistral34.1$0.15——
49▼ 1DeepSeek R1 Distill Llama 8BOpenDeepSeek34.0$0.040——
50▼ 1Gemma 3 12B InstructOpenGoogle33.8$0.063——

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 “—”.