Skip to content
IFAI

Model rankings

892 models · 5 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated December 23, 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 · #8 overall67.0
2MiMo-V2-Flash (Reasoning)Xiaomi · #10 overall66.1
3DeepSeek V3.2 (Reasoning)DeepSeek · #11 overall65.9
This week's changes
glm-4.7Coding · #5New
MiMo-V2-Flash (Reasoning)Intelligence · #10New
K2-V2 (high)Intelligence · #67New
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—Kimi K2 ThinkingOpenKimi67.0$1.1——
2NewMiMo-V2-Flash (Reasoning)OpenXiaomi · 1 more variant66.1$0.15——
3▼ 1DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant65.9$0.32——
4▼ 1MiniMax-M2OpenMiniMax61.4$0.52——
5▼ 1gpt-oss-120B (high)OpenOpenAI · 1 more variant60.5$0.26——
6▼ 1DeepSeek V3.2 SpecialeOpenDeepSeek58.6$0.32——
7▼ 1DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant57.7$0.80——
8▼ 1Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants57.5$2.6——
9▼ 1Apriel-v1.6-15B-ThinkerOpenServiceNow57.0$0.000——
10▼ 1DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant56.9$0.32——
11▼ 1GLM-4.6 (Reasoning)OpenZ AI · 1 more variant56.0$1.00——
12▼ 1Qwen3 VL 235B A22B (Reasoning)OpenAlibaba54.4$2.6——
13▼ 1Qwen3 Next 80B A3B (Reasoning)OpenAlibaba54.3$1.9——
14▼ 1DeepSeek V3.1 (Reasoning)OpenDeepSeek · 1 more variant54.0$0.86——
15▼ 1gpt-oss-20B (high)OpenOpenAI · 1 more variant52.1$0.10——
16▼ 1DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant52.0$1.7——
17▼ 1Qwen3 VL 32B (Reasoning)OpenAlibaba51.9$2.6——
18▼ 1NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant51.8$0.11——
19▼ 1Seed-OSS-36B-InstructOpenByteDance Seed51.6$0.30——
20▼ 1Apriel-v1.5-15B-ThinkerOpenServiceNow51.6$0.000——
21▼ 1GLM-4.5 (Reasoning)OpenZ AI51.3$1.0——
22▼ 1Kimi K2 0905OpenKimi · 1 more variant50.4$1.4——
23▼ 1GLM-4.5-AirOpenZ AI48.8$0.43——
24▼ 1Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants46.4$0.75——
25NewK2-V2 (high)OpenMBZUAI Institute of Foundation Models · 2 more variants46.3$0.000——
26▼ 2MiniMax M1 80kOpenMiniMax46.2$0.83——
27▼ 2Qwen3 235B A22B 2507 InstructOpenAlibaba45.3$1.2——
28▼ 2Qwen3 VL 30B A3B (Reasoning)OpenAlibaba45.3$0.75——
29▼ 2Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant45.2$0.18——
30▼ 2Qwen3 Next 80B A3B InstructOpenAlibaba44.8$0.88——
31▼ 2Ling-1TOpenInclusionAI44.8$1.00——
32▼ 2Qwen3 VL 235B A22B InstructOpenAlibaba44.2$1.2——
33▼ 2Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants43.4$0.000——
34▼ 2Magistral Small 1.2OpenMistral43.0$0.75——
35▼ 2EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant42.6$0.70——
36▼ 2Qwen3 Coder 480B A35B InstructOpenAlibaba42.3$3.0——
37▼ 2Ring-1TOpenInclusionAI41.8$0.99——
38▼ 2Hermes 4 - Llama-3.1 405B (Reasoning)OpenNous Research · 1 more variant41.6$1.5——
39▼ 2DeepSeek V3 0324OpenDeepSeek · 1 more variant41.3$1.2——
40▼ 2Qwen3 VL 32B InstructOpenAlibaba41.0$1.2——
41NewGLM-4.6V (Reasoning)OpenZ AI · 1 more variant40.8$0.45——
42▼ 3NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant40.7$0.30——
43▼ 3MiniMax M1 40kOpenMiniMax40.0$0.83——
44▼ 3Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba40.0$0.43——
45▼ 3Ring-flash-2.0OpenInclusionAI39.5$0.25——
46▼ 3Hermes 4 - Llama-3.1 70B (Reasoning)OpenNous Research · 1 more variant39.2$0.20——
47▼ 3Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant38.7$2.6——
48▼ 3Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA38.5$0.90——
49▼ 3Qwen3 VL 30B A3B InstructOpenAlibaba38.5$0.35——
50▼ 3Mistral Large 3OpenMistral38.4$0.75——

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 “—”.