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—gpt-oss-120B (high)OpenOpenAI · 1 more variant60.5$0.26——
2—gpt-oss-20B (high)OpenOpenAI · 1 more variant52.1$0.10——
3—Apriel-v1.5-15B-ThinkerOpenServiceNow51.6$0.000——
4—Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant45.2$0.18——
5NewNVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant40.7$0.30——
6▼ 1Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA38.5$0.90——
7▼ 1NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant37.2$0.070——
8▼ 1Llama 4 MaverickOpenMeta35.8$0.42——
9▼ 1Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant35.5$0.000——
10▼ 1Llama 4 ScoutOpenMeta28.1$0.24——
11▼ 1Llama 3.1 Instruct 405BOpenMeta28.1$4.5——
12▼ 1Llama 3.3 Instruct 70BOpenMeta27.9$0.58——
13▼ 1Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA26.1$0.000——
14▼ 1Grok 2 (Dec '24)OpenxAI24.7$4.0——
15▼ 1Llama 3.1 Nemotron Instruct 70BOpenNVIDIA23.6$0.60——
16▼ 1Granite 4.0 H SmallOpenIBM22.7$0.11——
17▼ 1Phi-4OpenMicrosoft Azure22.7$0.22——
18▼ 1Llama 3.1 Instruct 70BOpenMeta22.6$0.56——
19▼ 1Gemma 3 27B InstructOpenGoogle22.2$0.000——
20▼ 1Gemma 3 12B InstructOpenGoogle20.4$0.000——
21▼ 1R1 1776OpenPerplexity19.1$0.000——
22▼ 1Llama 3.2 Instruct 90B (Vision)OpenMeta18.9$0.72——
23▼ 1Grok-1OpenxAI18.2$0.000——
24▼ 1LFM2 8B A1BOpenLiquid AI17.4$0.000——
25—Llama 3.1 Instruct 8BOpenMeta16.9$0.10——
26—Granite 4.0 MicroOpenIBM16.2$0.000——
27—Phi-4 Mini InstructOpenMicrosoft Azure15.7$0.000——
28—Llama 3.2 Instruct 11B (Vision)OpenMeta15.5$0.16——
29—Gemma 3n E4B InstructOpenGoogle15.5$0.025——
30—Granite 3.3 8B (Non-reasoning)OpenIBM15.2$0.085——
31—Gemma 3 4B InstructOpenGoogle14.7$0.000——
32—Phi-3 Medium Instruct 14BOpenMicrosoft Azure14.4$0.30——
33—Granite 4.0 H 1BOpenIBM13.7$0.000——
34—Granite 4.0 1BOpenIBM13.3$0.000——
35—Llama 3 Instruct 70BOpenMeta13.0$0.71——
36—Phi-3 Mini Instruct 3.8BOpenMicrosoft Azure12.7$0.23——
37—Gemma 3n E4B Instruct Preview (May '25)OpenGoogle12.5$0.000——
38—Phi-4 Multimodal InstructOpenMicrosoft Azure12.4$0.000——
39—LFM2 2.6BOpenLiquid AI11.8$0.000——
40—Llama 2 Chat 7BOpenMeta11.3$0.10——
41—Gemma 3n E2B InstructOpenGoogle11.3$0.000——
42—Llama 3.2 Instruct 3BOpenMeta11.2$0.060——
43—LFM2 1.2BOpenLiquid AI9.7$0.000——
44—Llama 3.2 Instruct 1BOpenMeta8.9$0.053——
45—Granite 4.0 H 350MOpenIBM8.2$0.000——
46▲ 1Granite 4.0 350MOpenIBM7.7$0.000——
47▲ 1Arctic InstructOpenSnowflake7.6$0.000——
48▲ 1Llama 3 Instruct 8BOpenMeta7.0$0.073——
49▲ 1Gemma 3 1B InstructOpenGoogle6.8$0.000——
50▲ 1Gemma 3 270MOpenGoogle5.6$0.000——

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 “—”.