Skip to content
IFAI

Model rankings

391 models · 2 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated May 27, 2025

Smartest
o4-mini (high)OpenAI69.8Intelligence
Best open model
Qwen3 235B A22B (Reasoning)Alibaba62.3Intelligence
Best value
Gemma 3 4B InstructGoogle979 pts/$Value
Best from China
Qwen3 235B A22B (Reasoning)Alibaba62.3Intelligence
Top three by Intelligence
1o4-mini (high)OpenAI69.8
3o3OpenAI66.8
Top three open models
1Qwen3 235B A22B (Reasoning)Alibaba · #7 overall62.3
3DeepSeek R1DeepSeek · #11 overall60.2
This week's changes
Claude 4 OpusIntelligence · #14New
Grok 3 Reasoning BetaIntelligence · #16New
o1-proIntelligence · #16New
GPT-4.5 (Preview)Intelligence · #22New
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—o4-mini (high)ClosedOpenAI69.8$1.9——
2—Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle68.9$3.4——
3—o3ClosedOpenAI66.8$18——
4—Grok 3 mini Reasoning (high)ClosedxAI66.7$0.35——
5—o3-mini (high)ClosedOpenAI · 1 more variant65.5$1.9——
6▲ 1Gemini 2.5 Flash Preview (May '25) (Reasoning)ClosedGoogle · 3 more variants65.1$0.99——
7▼ 1o1ClosedOpenAI · 1 more variant61.9$26——
8NewClaude 4 Sonnet (Extended Thinking)ClosedAnthropic · 1 more variant60.8$6.0——
9NewClaude 4 OpusClosedAnthropic57.7$30——
10▼ 2Claude 3.7 Sonnet (Extended Thinking)ClosedAnthropic · 1 more variant57.4$6.0——
11NewGrok 3 Reasoning BetaClosedxAI56.1$0.000——
11Newo1-proClosedOpenAI56.1$263——
13▼ 4o1-miniClosedOpenAI53.8$1.9——
14NewGPT-4.5 (Preview)ClosedOpenAI53.0$94——
15▼ 5GPT-4.1 miniClosedOpenAI52.9$0.70——
16▼ 5GPT-4.1ClosedOpenAI52.6$3.5——
17▼ 5Gemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle · 1 more variant52.3$0.000——
18▼ 5Grok 3ClosedxAI50.6$6.0——
19▼ 5GPT-4o (March 2025, chatgpt-4o-latest)ClosedOpenAI · 4 more variants50.3$7.5——
20▼ 5Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle49.2$0.000——
21▼ 5Mistral Medium 3ClosedMistral49.0$0.80——
22NewSonar ReasoningClosedPerplexity48.8$2.0——
23▼ 6Gemini 2.0 Flash (Feb '25)ClosedGoogle · 1 more variant48.1$0.18——
24▼ 6Qwen2.5 MaxClosedAlibaba45.3$2.8——
25▼ 6Gemini 1.5 Pro (Sep '24)ClosedGoogle · 1 more variant44.6$2.2——
26▼ 6Claude 3.5 Sonnet (Oct '24)ClosedAnthropic · 1 more variant44.4$6.0——
27▼ 6SonarClosedPerplexity43.4$1.0——
28▼ 6Sonar ProClosedPerplexity42.7$6.0——
29▼ 6Nova PremierClosedAmazon42.6$5.0——
30▼ 6Gemini 2.0 Flash-Lite (Feb '25)ClosedGoogle · 1 more variant41.4$0.13——
31▼ 6GPT-4.1 nanoClosedOpenAI41.0$0.18——
32▼ 6Grok 2 (Dec '24)ClosedxAI39.2$0.000——
33▼ 6Gemini 1.5 Flash (Sep '24)ClosedGoogle · 1 more variant39.0$0.13——
34NewGPT-4 TurboClosedOpenAI38.8$15——
35▼ 7Grok BetaClosedxAI37.5$7.5——
36▼ 7Nova ProClosedAmazon37.1$1.4——
37NewGPT-4ClosedOpenAI36.0$38——
38▼ 8GPT-4o miniClosedOpenAI35.7$0.26——
39▼ 8Claude 3 OpusClosedAnthropic35.1$30——
40▼ 8Claude 3.5 HaikuClosedAnthropic34.7$1.6——
41NewSnowflake Llama 3.3 70BClosedSnowflake34.3$0.000——
42NewMistral SabaClosedMistral34.1$0.30——
43NewReka CoreClosedReka AI33.9$2.0——
44▼ 11Qwen2.5 TurboClosedAlibaba33.6$0.088——
45NewReka Flash (Sep '24)ClosedReka AI · 1 more variant33.6$0.35——
46NewReka EdgeClosedReka AI33.0$0.10——
47▼ 13Nova LiteClosedAmazon32.5$0.11——
48▼ 13Gemini 1.5 Flash-8BClosedGoogle30.8$0.066——
49▼ 13Nova MicroClosedAmazon28.3$0.061——
50▼ 13Yi-LargeClosed01.AI27.9$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 “—”.