Skip to content
IFAI

Model rankings

896 models · 5 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published November 9, 2026

Most preferred
Gemini 4 Carbon (High)Google1,526Score
Best open model
Kimi K3 (Max)Moonshot AI1,487Score
Best from China
Kimi K3 (Max)Moonshot AI1,487Score
Most voted
Claude 3 Opus (20240229)Anthropic194,909Votes
Top three by Score
Top three open models
1Kimi K3 (Max)Moonshot AI · #16 overall1,487
2Kimi K3.1 Pro (Max)Moonshot AI · #21 overall1,483
3GLM-5.3 (Max)Z.ai · #23 overall1,483
This week's changes
Simba 3.5Speech · #5New
Bach 1.0 ProVideo · #7New
RankChangeModelScore95% intervalVotesPrice $/M
1—Kimi K3 (Max)OpenMoonshot AI1,487±440,867$6.0
2NewKimi K3.1 Pro (Max)OpenMoonshot AI1,483±113,443$4.0
3▼ 1GLM-5.3 (Max)OpenZ.ai1,483±531,017$2.2
4▼ 1MiMo-V2.6-ProOpenXiaomi1,480±94,066$0.54
5▼ 1GLM-5.2 (Max)OpenZ.ai1,475±454,173—
6▼ 1DeepSeek-V4.1-Flash-20260910 (Max)OpenDeepSeek1,475±613,580—
7▼ 1GLM-5.3-FlashOpenZ.ai1,474±450,189$0.24
8▼ 1MiMo-V2.5-ProOpenXiaomi1,467±476,793—
9▼ 1GLM-5.1OpenZ.ai1,465±467,074—
10▼ 1DeepSeek-V4-Pro (High, 20260813)OpenDeepSeek1,464±79,584—
11▼ 1Kimi K2.6OpenMoonshot AI1,461±439,573—
12▼ 1DeepSeek-V4-ProOpenDeepSeek1,458±456,906—
13▼ 1GLM-5OpenZ.ai1,457±429,020—
14▼ 1DeepSeek-V4-Pro Preview (High)OpenDeepSeek1,455±454,233—
15▼ 1Hy3OpenTencent1,454±615,068—
16▼ 1Gemma 4 31BOpenGoogle1,452±76,130$0.000
17▼ 1Kimi K2.5 (Thinking)OpenMoonshot AI1,450±373,872—
18▼ 1MiMo-V2.6-FlashOpenXiaomi1,448±522,354$0.18
19▼ 1InklingOpenThinking Machines1,443±450,137$1.8
20—Qwen3.5-397B-A17BOpenAlibaba1,441±397,678—
21▼ 2GLM-4.7OpenZ.ai1,441±612,167—
22▼ 1DeepSeek-V4-Flash Preview (High)OpenDeepSeek1,439±451,195—
23▼ 1Gemma 4 26B A4BOpenGoogle1,437±76,075—
24▼ 1MiniMax-M3OpenMiniMax1,436±472,963$0.52
25▼ 1DeepSeek-V4-FlashOpenDeepSeek1,436±451,368—
26▼ 1Beam 1.0 501B A23BOpenReflection1,435±104,006—
27▼ 1MiMo-V2.5OpenXiaomi1,434±446,820—
28▼ 1Qwen3.8-27BOpenAlibaba1,433±532,659$1.1
29▼ 1Kimi K2.5 (Instant)OpenMoonshot AI1,431±78,323—
30▼ 1Kimi K2 Thinking TurboOpenMoonshot AI1,430±362,955—
31—Mistral Medium 3.5OpenMistral1,427±611,656$3.0
32▼ 2NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)OpenNVIDIA1,426±711,399—
33▼ 1DeepSeek-V3.2-Exp (Thinking)OpenDeepSeek1,425±78,966—
34▼ 1DeepSeek-V3.2OpenDeepSeek1,425±347,790—
35▼ 1Muse GlimmerOpenMeta1,425±103,793$0.52
36▼ 1GLM-4.6OpenZ.ai1,424±435,652—
37▲ 4Mistral Large 4OpenMistral1,423±95,742$1.0
38▼ 2DeepSeek-V3.2 (Thinking)OpenDeepSeek1,423±441,782—
39▼ 2Qwen3-235B-A22B-Instruct (2507)OpenAlibaba1,422±397,642—
40▼ 2DeepSeek-V3.2-ExpOpenDeepSeek1,422±611,955—
41▼ 2DeepSeek-R1 (0528)OpenDeepSeek1,421±618,153—
42▼ 2Kimi K2 Preview (0905)OpenMoonshot AI1,418±711,578—
43▼ 1Kimi K2 Preview (0711)OpenMoonshot AI1,418±527,099—
44▼ 1DeepSeek-V3.1OpenDeepSeek1,417±614,586—
45▼ 1Qwen3.5-122B-A10BOpenAlibaba1,416±429,496—
46▼ 1DeepSeek-V3.1-Terminus (Thinking)OpenDeepSeek1,416±103,361—
47▼ 1DeepSeek-V3.1 (Thinking)OpenDeepSeek1,416±711,441—
48▲ 1NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)OpenNVIDIA1,415±104,061—
49▼ 1MiniMax-M2.7OpenMiniMax1,415±389,504—
50▼ 3DeepSeek-V3.1-TerminusOpenDeepSeek1,415±103,605—

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 “—”.