Skip to content
IFAI

Model rankings

245 models · 2 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated February 25, 2025

Smartest
o3-miniOpenAI62.9Intelligence
Best open model
DeepSeek R1DeepSeek60.2Intelligence
Best from China
DeepSeek R1DeepSeek60.2Intelligence
Top three by Intelligence
1o3-miniOpenAI62.9
2o1OpenAI61.9
3DeepSeek R1DeepSeek60.2
Top three open models
1DeepSeek R1DeepSeek · #3 overall60.2
2DeepSeek R1 Distill Qwen 14BDeepSeek · #5 overall49.6
3DeepSeek V3DeepSeek · #8 overall45.7
This week's changes
DeepSeek R1 Distill Qwen 14BIntelligence · #5New
DeepSeek R1 Distill Qwen 32BIntelligence · #10New
DeepSeek R1 Distill Llama 70BIntelligence · #13New
Qwen2.5 Instruct 72BIntelligence · #19New
Phi-4Intelligence · #20New
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—o3-miniClosedOpenAI62.9———
2—o1ClosedOpenAI61.9———
3—DeepSeek R1OpenDeepSeek60.2———
4—o1-miniClosedOpenAI53.8———
5NewDeepSeek R1 Distill Qwen 14BOpenDeepSeek49.6———
6▼ 1Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle49.2———
7▲ 3Gemini 2.0 Flash (Feb '25)ClosedGoogle48.1———
8▼ 2DeepSeek V3OpenDeepSeek45.7———
9▼ 2Qwen2.5 MaxClosedAlibaba45.3———
10NewDeepSeek R1 Distill Qwen 32BOpenDeepSeek45.2———
11▼ 3Gemini 1.5 Pro (Sep '24)ClosedGoogle · 1 more variant44.6———
12▼ 3Claude 3.5 Sonnet (Oct '24)ClosedAnthropic44.3———
13NewDeepSeek R1 Distill Llama 70BOpenDeepSeek44.0———
14▼ 3QwQ 32B-PreviewOpenAlibaba42.6———
15▼ 3Gemini 2.0 Flash-Lite (Preview)ClosedGoogle41.9———
16▼ 3GPT-4o (Nov '24)ClosedOpenAI · 3 more variants41.5———
17▼ 3Llama 3.3 Instruct 70BOpenMeta41.1———
18▼ 3Llama 3.1 Instruct 405BOpenMeta40.5———
19NewQwen2.5 Instruct 72BOpenAlibaba40.3———
20NewPhi-4OpenMicrosoft Azure40.2———
21NewLlama 3.1 Tulu3 405BOpenAllen Institute for AI39.9———
22▼ 6MiniMax-Text-01OpenMiniMax39.9———
23▼ 6Mistral Large 2 (Nov '24)OpenMistral · 1 more variant38.3———
24NewGrok BetaClosedxAI37.5———
25▼ 7Pixtral LargeOpenMistral37.4———
26NewQwen2.5 Instruct 32BOpenAlibaba37.4———
27▼ 8Llama 3.1 Nemotron Instruct 70BOpenNVIDIA37.3———
28▼ 8Nova ProClosedAmazon37.1———
29▼ 8Qwen2.5 Coder Instruct 32BOpenAlibaba36.3———
30▼ 8GPT-4o miniClosedOpenAI35.7———
31NewDeepSeek R1 Distill Llama 8BOpenDeepSeek35.4———
32▼ 9Llama 3.1 Instruct 70BOpenMeta35.4———
33▼ 9Mistral Small 3OpenMistral35.3———
34▼ 9Claude 3 OpusClosedAnthropic35.1———
35▼ 9Claude 3.5 HaikuClosedAnthropic34.6———
36▼ 9Qwen TurboClosedAlibaba33.6———
37NewLlama 3.2 Instruct 90B (Vision)OpenMeta33.4———
38NewMistral SabaClosedMistral32.2———
39▼ 11Jamba 1.5 LargeOpenAI21 Labs29.3———
40NewGemini 1.5 Flash (May '24)ClosedGoogle28.4———
41▼ 12Nova MicroClosedAmazon28.3———
42▼ 12Yi-LargeClosed01.AI27.9———
43NewCodestral (Jan '25)ClosedMistral · 1 more variant27.6———
44▼ 13Llama 3 Instruct 70BOpenMeta27.5———
45▼ 13Mistral Small (Sep '24)OpenMistral · 1 more variant27.4———
46NewMistral Large (Feb '24)ClosedMistral26.4———
47NewMixtral 8x22B InstructOpenMistral26.2———
48NewPhi-3 Medium Instruct 14BOpenMicrosoft Azure24.5———
49NewMistral MediumClosedMistral23.9———
50▼ 17Llama 3.1 Instruct 8BOpenMeta23.7———

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 “—”.