Skip to content
IFAI

Model rankings

866 models · 5 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated December 9, 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
3GPT-5.1 (high)OpenAI69.7
Top three open models
1Kimi K2 ThinkingKimi · #6 overall67.0
2DeepSeek V3.2 (Reasoning)DeepSeek · #8 overall65.9
3MiniMax-M2MiniMax · #18 overall61.4
This week's changes
gpt-5.2Coding · #5New
GPT-5.1 Codex (high)Intelligence · #7New
DeepSeek V3.2 (Reasoning)Intelligence · #8New
Z-Image TurboImage · #9New
Nova 2.0 Pro Preview (medium)Intelligence · #16New
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—Gemini 3 Pro Preview (high)ClosedGoogle72.9$4.5——
2—Claude Opus 4.5 (Reasoning)ClosedAnthropic69.8$10——
3—GPT-5.1 (high)ClosedOpenAI69.7$3.4——
4—GPT-5 Codex (high)ClosedOpenAI68.5$3.4——
5—GPT-5 (high)ClosedOpenAI68.5$3.4——
6NewGPT-5.1 Codex (high)ClosedOpenAI66.9$3.4——
7▼ 1GPT-5 (medium)ClosedOpenAI66.4$3.4——
8▼ 1o3ClosedOpenAI65.5$3.5——
9▼ 1Grok 4ClosedxAI65.3$6.0——
10▼ 1o3-proClosedOpenAI65.3$35——
11NewGemini 3 Pro Preview (low)ClosedGoogle64.5$4.5——
12▼ 2GPT-5 mini (high)ClosedOpenAI64.3$0.69——
13▼ 2Grok 4.1 Fast (Reasoning)ClosedxAI64.1$0.28——
14▼ 2Claude 4.5 Sonnet (Reasoning)ClosedAnthropic62.7$6.0——
15NewNova 2.0 Pro Preview (medium)ClosedAmazon62.4$3.4——
16NewGPT-5.1 Codex mini (high)ClosedOpenAI62.3$0.69——
17▼ 4GPT-5 (low)ClosedOpenAI61.8$3.4——
18▼ 4GPT-5 mini (medium)ClosedOpenAI60.8$0.69——
19▼ 4gpt-oss-120B (high)OpenOpenAI60.5$0.26——
20▼ 4Grok 4 Fast (Reasoning)ClosedxAI60.3$0.28——
21▼ 4Claude Opus 4.5 (Non-reasoning)ClosedAnthropic59.9$10——
22▼ 4Gemini 2.5 ProClosedGoogle59.6$3.4——
23▼ 4o4-mini (high)ClosedOpenAI59.6$1.9——
24▼ 4Claude 4.1 Opus (Reasoning)ClosedAnthropic59.3$30——
25NewNova 2.0 Lite (medium)ClosedAmazon57.7$0.85——
26NewNova 2.0 Pro Preview (low)ClosedAmazon57.6$3.4——
27▼ 6Grok 3 mini Reasoning (high)ClosedxAI57.1$0.35——
28▼ 6Claude 4 Sonnet (Reasoning)ClosedAnthropic56.5$6.0——
29NewNova 2.0 Omni (medium)ClosedAmazon56.0$0.85——
30▼ 7Claude 4.5 Haiku (Reasoning)ClosedAnthropic54.6$2.0——
31▼ 7Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle54.4$0.85——
32▼ 7Claude 4 Opus (Reasoning)ClosedAnthropic54.2$30——
33▼ 7Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle54.1$3.4——
34▼ 7Gemini 2.5 Pro Preview (May' 25)ClosedGoogle53.2$3.4——
35▼ 7gpt-oss-20B (high)OpenOpenAI52.1$0.10——
36▼ 7Apriel-v1.5-15B-ThinkerOpenServiceNow51.6$0.000——
37▼ 7Gemini 2.5 Flash (Reasoning)ClosedGoogle51.2$0.85——
38▼ 7GPT-5 nano (high)ClosedOpenAI51.0$0.14——
39▼ 7o3-mini (high)ClosedOpenAI50.8$1.9——
40▼ 7Claude 3.7 Sonnet (Reasoning)ClosedAnthropic49.9$6.0——
41▼ 7Claude 4.5 Sonnet (Non-reasoning)ClosedAnthropic49.6$6.0——
42▼ 7GPT-5 nano (medium)ClosedOpenAI49.3$0.14——
43NewNova 2.0 Omni (low)ClosedAmazon48.7$0.85——
44▼ 8Grok Code Fast 1ClosedxAI48.7$0.53——
45▼ 8o3-miniClosedOpenAI48.1$1.9——
46▼ 8o1-proClosedOpenAI48.0$263——
47▼ 8Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle47.9$0.18——
48▼ 8gpt-oss-120B (low)OpenOpenAI47.5$0.26——
49▼ 8o1ClosedOpenAI47.2$26——
50NewNova 2.0 Lite (low)ClosedAmazon46.8$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 “—”.