Skip to content
IFAI

Model rankings

656 models · 3 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated October 7, 2025

Smartest
GPT-5 Codex (high)OpenAI68.5Intelligence
Best open model
gpt-oss-120B (high)OpenAI58.0Intelligence
Best value
Gemma 3n E4B InstructGoogle620 pts/$Value
Best from China
DeepSeek V3.1 Terminus (Reasoning)DeepSeek57.7Intelligence
Top three by Intelligence
1GPT-5 Codex (high)OpenAI68.5
2GPT-5 (high)OpenAI68.5
3o3OpenAI65.5
Top three open models
1gpt-oss-120B (high)OpenAI · #12 overall58.0
2DeepSeek V3.1 Terminus (Reasoning)DeepSeek · #13 overall57.7
3Qwen3 235B A22B 2507 (Reasoning)Alibaba · #14 overall57.5
This week's changes
DeepSeek V3.2 Exp (Reasoning)Intelligence · #16New
GLM-4.6 (Reasoning)Intelligence · #18New
Apriel-v1.5-15B-ThinkerIntelligence · #27New
Qwen3 4B 2507 InstructIntelligence · #88New
Granite 4.0 H SmallIntelligence · #122New
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1▲ 1GPT-5 Codex (high)ClosedOpenAI68.5$3.4——
2▼ 1GPT-5 (high)ClosedOpenAI68.5$3.4——
3—GPT-5 (medium)ClosedOpenAI66.4$3.4——
4—o3ClosedOpenAI65.5$3.5——
5—Grok 4ClosedxAI65.3$6.0——
6—o3-proClosedOpenAI65.3$35——
7—GPT-5 mini (high)ClosedOpenAI64.3$0.69——
8▲ 1Claude 4.5 Sonnet (Reasoning)ClosedAnthropic62.7$6.0——
9▼ 1GPT-5 (low)ClosedOpenAI61.8$3.4——
10—GPT-5 mini (medium)ClosedOpenAI60.8$0.69——
11—Grok 4 Fast (Reasoning)ClosedxAI60.3$0.28——
12—Gemini 2.5 ProClosedGoogle59.6$3.4——
13—o4-mini (high)ClosedOpenAI59.6$1.9——
14—Claude 4.1 Opus (Reasoning)ClosedAnthropic59.3$30——
15—gpt-oss-120B (high)OpenOpenAI58.0$0.26——
16—Grok 3 mini Reasoning (high)ClosedxAI57.1$0.35——
17—Claude 4 Sonnet (Reasoning)ClosedAnthropic56.5$6.0——
18—Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle54.4$0.85——
19—Claude 4 Opus (Reasoning)ClosedAnthropic54.2$30——
20—Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle54.1$3.4——
21—Gemini 2.5 Pro Preview (May' 25)ClosedGoogle53.2$3.4——
22NewApriel-v1.5-15B-ThinkerOpenServiceNow51.6$0.000——
23▼ 1Gemini 2.5 Flash (Reasoning)ClosedGoogle51.2$0.85——
24▼ 1GPT-5 nano (high)ClosedOpenAI51.0$0.14——
25▼ 1o3-mini (high)ClosedOpenAI50.8$1.9——
26▼ 1Claude 3.7 Sonnet (Reasoning)ClosedAnthropic49.9$6.0——
27▲ 1Claude 4.5 Sonnet (Non-reasoning)ClosedAnthropic49.6$6.0——
28▼ 2GPT-5 nano (medium)ClosedOpenAI49.3$0.14——
29▼ 2Grok Code Fast 1ClosedxAI48.7$0.53——
30▼ 1o3-miniClosedOpenAI48.1$1.9——
31▼ 1o1-proClosedOpenAI48.0$263——
32▼ 1Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle47.9$0.18——
33▼ 1o1ClosedOpenAI47.2$26——
34▼ 1Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)ClosedGoogle46.7$0.85——
35▼ 1Sonar Reasoning ProClosedPerplexity46.3$0.000——
36▼ 1Gemini 2.5 Flash Preview (Reasoning)ClosedGoogle45.8$0.000——
37▼ 1Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA45.2$0.18——
38▼ 1o1-previewClosedOpenAI44.9$29——
39▼ 1Claude 4.1 Opus (Non-reasoning)ClosedAnthropic44.6$30——
40▼ 1Claude 4 Sonnet (Non-reasoning)ClosedAnthropic44.4$6.0——
41▼ 1GPT-5 (minimal)ClosedOpenAI43.5$3.4——
42▼ 1GPT-4.1ClosedOpenAI43.4$3.5——
43▼ 1gpt-oss-20B (high)OpenOpenAI43.3$0.095——
44▼ 1GPT-4.1 miniClosedOpenAI42.5$0.70——
45▼ 1Claude 4 Opus (Non-reasoning)ClosedAnthropic42.3$30——
46▼ 1GPT-5 (ChatGPT)ClosedOpenAI41.8$3.4——
47▼ 1Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)ClosedGoogle41.6$0.18——
48▼ 1GPT-5 mini (minimal)ClosedOpenAI41.6$0.69——
49▼ 1Grok 3 Reasoning BetaClosedxAI41.4$0.000——
50▼ 1Gemini 2.5 Flash (Non-reasoning)ClosedGoogle40.4$0.85——

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 “—”.