Skip to content
IFAI

Model rankings

1542 models · 5 boards · 2 sources

‹
Week of October 12, 2026
November 9, 202636 changesNovember 2, 202641 changesOctober 26, 20269 changesOctober 19, 2026247 changesOctober 12, 2026127 changesOctober 5, 202634 changesSeptember 28, 202617 changesSeptember 21, 2026115 changesSeptember 14, 2026174 changesSeptember 7, 2026144 changesAugust 31, 202620 changesAugust 24, 202615 changes
›
Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated October 12, 2026

Smartest
Claude Opus 5.5 (Max, Default Fallback)Anthropic57.6Intelligence
Best open model
MiMo-V2.6-ProXiaomi46.3Intelligence
Best value
Hy3-preview (Reasoning)Tencent228 pts/$Value
Best from China
MiMo-V2.6-ProXiaomi46.3Intelligence
Top three by Intelligence
1Claude Opus 5.5 (Max, Default Fallback)Anthropic57.6
2Claude Sonnet 5.5 (Max, Default Fallback)Anthropic56.0
3Claude Fable 5.1 (Max, Default Fallback)Anthropic53.4
Top three open models
1MiMo-V2.6-ProXiaomi · #13 overall46.3
2GLM-5.3 (Max)Z AI · #15 overall44.8
3Kimi K3 (Max)Kimi · #18 overall43.6
This week's changes
Claude Opus 5.5 (Max)Coding · #1New
Eleven v4 TurboSpeech · #1New
GPT-6 Astra (Max)Coding · #2New
Claude Sonnet 5.5 (xHigh)Coding · #3New
GPT-6.1 Sol (Max)Coding · #4New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortIntelligenceValueSpeedLowest price
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—Claude Opus 5.5 (Max, Default Fallback)ClosedAnthropic · 4 more variants57.6$8.097749 s
2—Claude Sonnet 5.5 (Max, Default Fallback)ClosedAnthropic · 4 more variants56.0$4.0137493 s
3—Claude Fable 5.1 (Max, Default Fallback)ClosedAnthropic · 4 more variants53.4$2065260 s
4—GPT-6 Astra (Max)ClosedOpenAI · 4 more variants52.7$2063391 s
5—Gemini 4 Argon (High)ClosedGoogle52.6$4.0——
6—GPT-6.1 Sol (Max)ClosedOpenAI · 4 more variants51.8$4.065348 s
7—Claude Opus 5 (Max)ClosedAnthropic · 4 more variants50.8$105467 s
8—Claude Fable 5 (Max, Opus 4.8 Fallback)ClosedAnthropic49.6$2066135 s
9—Muse Spark 1.3 (Max)ClosedMeta · 1 more variant48.1$2.012249 s
10—GPT-6 Sol (Max)ClosedOpenAI · 5 more variants47.6$4.0117144 s
11—GPT-5.6 Sol (Max)ClosedOpenAI · 5 more variants47.0$8.090124 s
12—Grok 4.7 (Xhigh)ClosedSpaceXAI · 2 more variants46.4$3.08388 s
13—MiMo-V2.6-ProOpenXiaomi46.3$0.54493.5 s
14—Qwen3.8 Max (0902)ClosedAlibaba · 1 more variant45.4$3.0362.8 s
15—GLM-5.3 (Max)OpenZ AI · 1 more variant44.8$2.2683.2 s
16—Grok 4.6 (High)ClosedSpaceXAI · 3 more variants44.3$3.06147 s
17—Step 5 PreviewClosedStepFun43.7$1.4892.9 s
18—Kimi K3 (Max)OpenKimi · 1 more variant43.6$6.0413.3 s
19NewClaude Haiku 5.5 (Max)ClosedAnthropic · 4 more variants43.4$0.20235300 s
20▼ 1GPT-5.6 Terra (Max)ClosedOpenAI · 5 more variants42.1$4.5126149 s
21▼ 1GLM-5.3-FlashOpenZ AI41.8$0.24613.0 s
22▼ 1Claude Opus 4.8 (Max)ClosedAnthropic41.8$106040 s
23▼ 1Ling 3.1 FlashClosedInclusionAI41.1$0.452131.9 s
24▼ 1Gemini 3.8 Flash (High)ClosedGoogle · 2 more variants40.9$1.513121 s
25▼ 1Claude Opus 4.7 (Max)ClosedAnthropic · 1 more variant40.7$105322 s
26▼ 1Qwen3.8 2.4T A95BOpenAlibaba39.9$3.0373.0 s
27▼ 1Qwen3.8-Flash-NextOpenAlibaba39.8$0.23512.0 s
28▼ 1Gemini 3.7 Flash (Medium)ClosedGoogle · 2 more variants39.6$1.53305.9 s
29▼ 1Muse Spark 1.2 (Xhigh)ClosedMeta39.6$2.031013 s
30▼ 1DeepSeek V4.1 Flash (Max)OpenDeepSeek · 1 more variant39.5$0.522141.0 s
31▼ 1GPT-5.4 (Xhigh)ClosedOpenAI · 2 more variants39.0$5.699192 s
32▼ 1Grok 4.5 (High)ClosedSpaceXAI38.8$3.05217 s
33NewMistral Large 4 PreviewClosedMistral38.4$2.1——
34▼ 2GPT-5.5 (Xhigh)ClosedOpenAI · 4 more variants38.4$119971 s
35▼ 2Claude Sonnet 5 (Max)ClosedAnthropic · 5 more variants38.2$4.079214 s
36▼ 2GPT-6 Luna (Max)ClosedOpenAI · 5 more variants38.1$0.20140102 s
37▼ 2MiMo-V2.6-FlashOpenXiaomi37.9$0.18493.4 s
38▼ 2GPT-5.6 Luna (Max)ClosedOpenAI · 5 more variants37.3$0.45121113 s
39▼ 2DeepSeek V4 Pro 0813 (Max)OpenDeepSeek · 4 more variants36.0$2.0931.6 s
40▼ 2DeepSeek V4 Flash Vision (Max)ClosedDeepSeek34.8$0.662261.0 s
41▼ 2DeepSeek V4 Flash 0731 (Max)OpenDeepSeek · 3 more variants34.3$0.662171.3 s
42▼ 2Gemini 3.6 Flash (High)ClosedGoogle34.0$1.519714 s
43▼ 2JT-4.1 Flash 236B A21B (Reasoning)ClosedChina Mobile · 1 more variant33.9———
44▼ 2Muse Spark 1.1 (Xhigh)ClosedMeta33.7$2.08534 s
45▼ 2GLM-5.2 (Max)OpenZ AI · 1 more variant33.7$2.2883.5 s
46▼ 2Qwen3.8 27B (Xhigh)OpenAlibaba · 3 more variants33.7$1.1473.8 s
47▼ 2Gemini 3.5 Flash (Medium)ClosedGoogle · 2 more variants33.6$3.420513 s
48▼ 2Motif 3OpenMotif Technologies · 1 more variant33.6———
49▼ 2GPT-5.3 Codex (Xhigh)ClosedOpenAI32.5$4.811573 s
50▼ 2Claude Opus 4.6 (Max)ClosedAnthropic · 1 more variant31.9$104626 s

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 “—”.