Skip to content
IFAI

Model rankings

880 models · 5 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated December 16, 2025

Smartest
Gemini 3 Pro Preview (high)Google72.9Intelligence
Best open model
Kimi K2 ThinkingKimi67.0Intelligence
Best value
Gemma 3n E4B InstructGoogle620 pts/$Value
Best from China
Kimi K2 ThinkingKimi67.0Intelligence
Top three by Intelligence
2GPT-5.2 (xhigh)OpenAI72.6
Top three open models
1Kimi K2 ThinkingKimi · #7 overall67.0
2DeepSeek V3.2 (Reasoning)DeepSeek · #9 overall65.9
3MiniMax-M2MiniMax · #19 overall61.4
This week's changes
GPT-5.2 (xhigh)Intelligence · #2New
gemini-3-flashCoding · #4New
deepseek-v3.2-thinkingCoding · #12New
Apriel-v1.6-15B-ThinkerIntelligence · #31New
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—Gemini 3 Pro Preview (high)ClosedGoogle · 1 more variant72.9$4.5——
2NewGPT-5.2 (xhigh)ClosedOpenAI72.6$4.8——
3▼ 1Claude Opus 4.5 (Reasoning)ClosedAnthropic · 1 more variant69.8$10——
4▼ 1GPT-5.1 (high)ClosedOpenAI · 1 more variant69.7$3.4——
5▼ 1GPT-5 Codex (high)ClosedOpenAI68.5$3.4——
6▼ 1GPT-5 (high)ClosedOpenAI · 4 more variants68.5$3.4——
7▼ 1GPT-5.1 Codex (high)ClosedOpenAI66.9$3.4——
8▼ 1o3ClosedOpenAI65.5$3.5——
9▼ 1Grok 4ClosedxAI65.3$6.0——
10▼ 1o3-proClosedOpenAI65.3$35——
11▼ 1GPT-5 mini (high)ClosedOpenAI · 2 more variants64.3$0.69——
12▼ 1Grok 4.1 Fast (Reasoning)ClosedxAI · 1 more variant64.1$0.28——
13▼ 1Claude 4.5 Sonnet (Reasoning)ClosedAnthropic · 1 more variant62.7$6.0——
14▼ 1Nova 2.0 Pro Preview (medium)ClosedAmazon · 2 more variants62.4$3.4——
15▼ 1GPT-5.1 Codex mini (high)ClosedOpenAI62.3$0.69——
16▼ 1gpt-oss-120B (high)OpenOpenAI · 1 more variant60.5$0.26——
17▼ 1Grok 4 Fast (Reasoning)ClosedxAI · 1 more variant60.3$0.28——
18▼ 1Gemini 2.5 ProClosedGoogle59.6$3.4——
19▼ 1o4-mini (high)ClosedOpenAI59.6$1.9——
20▼ 1Claude 4.1 Opus (Reasoning)ClosedAnthropic · 1 more variant59.3$30——
21▼ 1Nova 2.0 Lite (medium)ClosedAmazon · 2 more variants57.7$0.85——
22▼ 1Grok 3 mini Reasoning (high)ClosedxAI57.1$0.35——
23NewApriel-v1.6-15B-ThinkerOpenServiceNow57.0$0.000——
24▼ 2Claude 4 Sonnet (Reasoning)ClosedAnthropic · 1 more variant56.5$6.0——
25▼ 2Nova 2.0 Omni (medium)ClosedAmazon · 2 more variants56.0$0.85——
26▼ 2Claude 4.5 Haiku (Reasoning)ClosedAnthropic · 1 more variant54.6$2.0——
27▼ 2Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle · 3 more variants54.4$0.85——
28▼ 2Claude 4 Opus (Reasoning)ClosedAnthropic · 1 more variant54.2$30——
29▼ 2Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle · 1 more variant54.1$3.4——
30▼ 2gpt-oss-20B (high)OpenOpenAI · 1 more variant52.1$0.10——
31NewNVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA51.8$0.11——
32▼ 3Apriel-v1.5-15B-ThinkerOpenServiceNow51.6$0.000——
33▼ 3Gemini 2.5 Flash (Reasoning)ClosedGoogle · 1 more variant51.2$0.85——
34▼ 3GPT-5 nano (high)ClosedOpenAI · 2 more variants51.0$0.14——
35▼ 3o3-mini (high)ClosedOpenAI · 1 more variant50.8$1.9——
36▼ 3Claude 3.7 Sonnet (Reasoning)ClosedAnthropic · 1 more variant49.9$6.0——
37▼ 3Grok Code Fast 1ClosedxAI48.7$0.53——
38▼ 3o1-proClosedOpenAI48.0$263——
39▼ 3Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle · 1 more variant47.9$0.18——
40▼ 3o1ClosedOpenAI · 1 more variant47.2$26——
41▼ 3Sonar Reasoning ProClosedPerplexity46.3$0.000——
42▼ 3Grok 3ClosedxAI45.3$6.0——
43▼ 3Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant45.2$0.18——
44▼ 3GPT-4.1ClosedOpenAI43.4$3.5——
45▼ 3GPT-4.1 miniClosedOpenAI42.5$0.70——
46▼ 3Grok 3 Reasoning BetaClosedxAI41.4$0.000——
47▼ 3NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant40.7$0.30——
48▼ 3Gemini 2.5 Flash-Lite (Reasoning)ClosedGoogle · 1 more variant40.1$0.18——
49▼ 3o1-miniClosedOpenAI39.2$0.000——
50▼ 3Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA38.5$0.90——

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 “—”.