Skip to content
IFAI

Model rankings

481 models · 3 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated August 4, 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
3GLM-4.5Z AI · #10 overall65.7
This week's changes
GLM-4.5Intelligence · #10New
EXAONE 4.0 32B (Reasoning)Intelligence · #14New
Sonar Reasoning ProIntelligence · #21New
GLM-4.5-AirIntelligence · #24New
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—Grok 4ClosedxAI73.2$6.0——
2—o3-proClosedOpenAI71.0$35——
3—Gemini 2.5 ProClosedGoogle70.5$3.4——
4—o3ClosedOpenAI70.0$3.5——
5—o4-mini (high)ClosedOpenAI69.8$1.9——
6—Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba68.9$2.6——
7—Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle68.9$3.4——
8—DeepSeek R1 0528 (May '25)OpenDeepSeek68.3$0.96——
9—Gemini 2.5 Pro Preview (May' 25)ClosedGoogle67.9$3.4——
10—Grok 3 mini Reasoning (high)ClosedxAI66.7$0.35——
11NewGLM-4.5OpenZ AI65.7$0.94——
12▼ 1o3-mini (high)ClosedOpenAI65.5$1.9——
13▼ 1Gemini 2.5 Flash (Reasoning)ClosedGoogle65.1$0.85——
14▼ 1Claude 4 Opus (Extended Thinking)ClosedAnthropic64.4$30——
15NewEXAONE 4.0 32B (Reasoning)OpenLG AI Research64.1$0.70——
16▼ 1Claude 4 Sonnet (Extended Thinking)ClosedAnthropic63.8$6.0——
17NewLlama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA63.8$0.000——
18NewQwen3 30B A3B 2507 (Reasoning)OpenAlibaba63.4$0.75——
19▼ 5MiniMax M1 80kOpenMiniMax63.0$0.83——
20▼ 4o3-miniClosedOpenAI62.9$1.9——
21▼ 4Qwen3 235B A22B (Reasoning)OpenAlibaba62.3$2.6——
22▼ 4o1ClosedOpenAI61.9$26——
23▼ 4MiniMax M1 40kOpenMiniMax61.4$0.83——
24NewSonar Reasoning ProClosedPerplexity61.0$0.000——
25▼ 5Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA60.8$0.90——
26▼ 5Gemini 2.5 Flash Preview (Reasoning)ClosedGoogle60.5$0.99——
27▼ 5Qwen3 235B A22B 2507 (Non-reasoning)OpenAlibaba60.4$1.2——
28▼ 5DeepSeek R1 (Jan '25)OpenDeepSeek60.2$1.8——
29NewGLM-4.5-AirOpenZ AI59.8$0.43——
30▼ 5Qwen3 32B (Reasoning)OpenAlibaba59.2$2.6——
31▼ 5Solar Pro 2 (Reasoning)ClosedUpstage58.2$0.50——
32▼ 5QwQ 32BOpenAlibaba58.1$0.47——
33▼ 5Claude 4 OpusClosedAnthropic57.7$30——
34▼ 5Kimi K2OpenMoonshot AI57.6$1.1——
35▼ 5Claude 3.7 Sonnet (Extended Thinking)ClosedAnthropic57.4$6.0——
36NewQwen3 30B A3B 2507 (Non-reasoning)OpenAlibaba56.6$0.35——
37▼ 6Grok 3 Reasoning BetaClosedxAI56.1$0.000——
37▼ 6o1-proClosedOpenAI56.1$263——
39▼ 6Magistral MediumClosedMistral56.0$2.8——
40▼ 6Qwen3 14B (Reasoning)OpenAlibaba55.7$1.3——
41▼ 6Qwen3 30B A3B (Reasoning)OpenAlibaba55.6$0.75——
42▼ 6Gemini 2.5 Flash-Lite (Reasoning)ClosedGoogle54.9$0.18——
43▼ 6Magistral SmallOpenMistral54.7$0.75——
44▼ 6o1-miniClosedOpenAI53.8$1.9——
45▼ 6Qwen3 Coder 480B A35BOpenAlibaba53.7$3.0——
46▲ 86R1 1776OpenPerplexity53.7$3.5——
47▼ 7Gemini 2.5 FlashClosedGoogle53.4$0.85——
48▲ 10Sonar ReasoningClosedPerplexity53.4$2.0——
49▼ 8DeepSeek V3 0324 (Mar '25)OpenDeepSeek53.2$0.48——
50▼ 8Claude 4 SonnetClosedAnthropic53.0$6.0——

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 “—”.