Skip to content
IFAI

Model rankings

262 models · 2 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated March 4, 2025

Smartest
o3-mini (high)OpenAI65.5Intelligence
Best open model
DeepSeek R1DeepSeek60.2Intelligence
Best from China
DeepSeek R1DeepSeek60.2Intelligence
Top three by Intelligence
1o3-mini (high)OpenAI65.5
2o1OpenAI61.9
3DeepSeek R1DeepSeek60.2
Top three open models
1DeepSeek R1DeepSeek · #3 overall60.2
2DeepSeek R1 Distill Qwen 32BDeepSeek · #6 overall51.0
3DeepSeek R1 Distill Qwen 14BDeepSeek · #8 overall49.0
This week's changes
Qwen2 Instruct 72BIntelligence · #39New
Claude 3 SonnetIntelligence · #45New
Qwen2.5 Coder Instruct 7BIntelligence · #51New
Claude 2.1Intelligence · #53New
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1Newo3-mini (high)ClosedOpenAI65.5———
2▼ 1o3-miniClosedOpenAI62.9———
3▼ 1o1ClosedOpenAI61.9———
4▼ 1DeepSeek R1OpenDeepSeek60.2———
5NewClaude 3.7 Sonnet (Extended Thinking)ClosedAnthropic57.4———
6▼ 2o1-miniClosedOpenAI53.8———
7▲ 3DeepSeek R1 Distill Qwen 32BOpenDeepSeek51.0———
8▼ 2Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle49.2———
9▼ 4DeepSeek R1 Distill Qwen 14BOpenDeepSeek49.0———
10▲ 3DeepSeek R1 Distill Llama 70BOpenDeepSeek48.2———
11NewClaude 3.7 Sonnet (Standard)ClosedAnthropic48.2———
12▼ 5Gemini 2.0 Flash (Feb '25)ClosedGoogle48.1———
13▼ 5DeepSeek V3OpenDeepSeek45.7———
14▼ 5Qwen2.5 MaxClosedAlibaba45.3———
15▼ 4Gemini 1.5 Pro (Sep '24)ClosedGoogle44.6———
16▼ 4Claude 3.5 Sonnet (Oct '24)ClosedAnthropic44.3———
17▼ 3QwQ 32B-PreviewOpenAlibaba42.6———
18▼ 3Gemini 2.0 Flash-Lite (Preview)ClosedGoogle41.9———
19▼ 3GPT-4o (Nov '24)ClosedOpenAI41.5———
20▼ 3Llama 3.3 Instruct 70BOpenMeta41.1———
21▼ 3GPT-4o (ChatGPT)ClosedOpenAI41.1———
22▼ 3GPT-4o (Aug '24)ClosedOpenAI40.9———
23▼ 3GPT-4o (May '24)ClosedOpenAI40.9———
24▼ 3Llama 3.1 Instruct 405BOpenMeta40.5———
25▼ 3Qwen2.5 Instruct 72BOpenAlibaba40.3———
26▼ 3Phi-4OpenMicrosoft Azure40.2———
27▼ 3Llama 3.1 Tulu3 405BOpenAllen Institute for AI39.9———
28▼ 3MiniMax-Text-01OpenMiniMax39.9———
29▼ 3Mistral Large 2 (Nov '24)OpenMistral38.3———
30▼ 3Grok BetaClosedxAI37.5———
31▼ 3Pixtral LargeOpenMistral37.4———
32▼ 3Qwen2.5 Instruct 32BOpenAlibaba37.4———
33▼ 3Llama 3.1 Nemotron Instruct 70BOpenNVIDIA37.3———
34▼ 3Nova ProClosedAmazon37.1———
35▼ 3Mistral Large 2 (Jul '24)OpenMistral36.6———
36▼ 3Qwen2.5 Coder Instruct 32BOpenAlibaba36.3———
37▼ 3GPT-4o miniClosedOpenAI35.7———
38▼ 2Llama 3.1 Instruct 70BOpenMeta35.4———
39▼ 2Mistral Small 3OpenMistral35.3———
40▼ 2Claude 3 OpusClosedAnthropic35.1———
41▼ 2Claude 3.5 HaikuClosedAnthropic34.6———
42▼ 7DeepSeek R1 Distill Llama 8BOpenDeepSeek34.0———
43▼ 3Gemini 1.5 Pro (May '24)ClosedGoogle33.7———
44▼ 3Qwen TurboClosedAlibaba33.6———
45▼ 3Llama 3.2 Instruct 90B (Vision)OpenMeta33.4———
46NewQwen2 Instruct 72BOpenAlibaba32.6———
47▼ 4Mistral SabaClosedMistral32.2———
48▼ 4Jamba 1.5 LargeOpenAI21 Labs29.3———
49▼ 4Gemini 1.5 Flash (May '24)ClosedGoogle28.4———
50▼ 4Nova MicroClosedAmazon28.3———

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 “—”.