Skip to content
IFAI

Model rankings

521 models · 3 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated September 1, 2025

Smartest
GPT-5 (high)OpenAI69.0Intelligence
Best open model
Qwen3 235B A22B 2507 (Reasoning)Alibaba63.6Intelligence
Best value
Gemma 3n E4B InstructGoogle739 pts/$Value
Best from China
Qwen3 235B A22B 2507 (Reasoning)Alibaba63.6Intelligence
Top three by Intelligence
1GPT-5 (high)OpenAI69.0
2Grok 4xAI67.5
3o3-proOpenAI67.5
Top three open models
1Qwen3 235B A22B 2507 (Reasoning)Alibaba · #8 overall63.6
2gpt-oss-120BOpenAI · #9 overall61.3
3DeepSeek V3.1 (Reasoning)DeepSeek · #11 overall59.7
This week's changes
Exaone 4.0 1.2B (Reasoning)Intelligence · #81New
Qwen3 4B 2507 (Reasoning)Intelligence · #26Up 59
Qwen3 0.6B (Reasoning)Intelligence · #148Up 10
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—GPT-5 (high)ClosedOpenAI69.0$3.4——
2—GPT-5 (medium)ClosedOpenAI67.5$3.4——
3—Grok 4ClosedxAI67.5$6.0——
4—o3-proClosedOpenAI67.5$35——
5—o3ClosedOpenAI67.1$3.5——
6—GPT-5 mini (high)ClosedOpenAI65.4$0.69——
7—o4-mini (high)ClosedOpenAI65.1$1.9——
8—Gemini 2.5 ProClosedGoogle64.6$3.4——
9—GPT-5 mini (medium)ClosedOpenAI63.7$0.69——
10—Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba63.6$2.6——
11—GPT-5 (low)ClosedOpenAI63.4$3.4——
12—gpt-oss-120BOpenOpenAI61.3$0.26——
13—Claude 4.1 Opus (Extended Thinking)ClosedAnthropic61.0$30——
14—DeepSeek V3.1 (Reasoning)OpenDeepSeek59.7$0.96——
15—Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle59.0$3.4——
16—Claude 4 Sonnet (Extended Thinking)ClosedAnthropic58.8$6.0——
17—DeepSeek R1 0528 (May '25)OpenDeepSeek58.6$0.96——
18—Gemini 2.5 Flash (Reasoning)ClosedGoogle58.4$0.85——
19—Grok 3 mini Reasoning (high)ClosedxAI58.0$0.35——
20—Gemini 2.5 Pro Preview (May' 25)ClosedGoogle58.0$3.4——
21—GLM-4.5OpenZ AI56.1$0.99——
22—o3-mini (high)ClosedOpenAI55.5$1.9——
23—Claude 4 Opus (Extended Thinking)ClosedAnthropic55.3$30——
24—GPT-5 nano (high)ClosedOpenAI54.7$0.14——
25—Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba53.9$0.75——
26—GPT-5 nano (medium)ClosedOpenAI53.8$0.14——
27—MiniMax M1 80kOpenMiniMax53.2$0.83——
28—GLM-4.5-AirOpenZ AI52.8$0.43——
29—o3-miniClosedOpenAI52.7$1.9——
30—DeepSeek R1 (Jan '25)OpenDeepSeek52.7$1.8——
31—Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA52.4$0.000——
32—o1ClosedOpenAI51.7$26——
33NewQwen3 4B 2507 (Reasoning)OpenAlibaba50.8$0.000——
34▼ 1Qwen3 235B A22B 2507 (Non-reasoning)OpenAlibaba50.7$1.2——
35▼ 1Sonar Reasoning ProClosedPerplexity50.7$0.000——
36▼ 1EXAONE 4.0 32B (Reasoning)OpenLG AI Research50.7$0.70——
37▼ 1Gemini 2.5 Flash Preview (Reasoning)ClosedGoogle50.2$0.99——
38▼ 1o1-previewClosedOpenAI49.3$29——
39▼ 1gpt-oss-20BOpenOpenAI49.0$0.088——
40▼ 1Claude 4.1 OpusClosedAnthropic49.0$30——
41▼ 1DeepSeek V3.1 (Non-reasoning)OpenDeepSeek48.8$0.48——
42▼ 1Kimi K2OpenMoonshot AI48.6$1.1——
43▼ 1Qwen3 235B A22B (Reasoning)OpenAlibaba48.4$2.6——
44▼ 1Gemini 2.5 FlashClosedGoogle47.3$0.85——
45▼ 1Gemini 2.5 Flash-Lite (Reasoning)ClosedGoogle47.3$0.18——
46▼ 1Claude 3.7 Sonnet (Extended Thinking)ClosedAnthropic47.0$6.0——
47▼ 1GPT-4.1ClosedOpenAI46.8$3.5——
48▼ 1Claude 4 OpusClosedAnthropic46.6$30——
49▼ 1Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA46.4$0.90——
50▼ 1GPT-5 mini (minimal)ClosedOpenAI46.3$0.69——

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 “—”.