Skip to content
IFAI

Model rankings

1492 models · 5 boards · 2 sources

‹
Week of September 7, 2026
October 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 changesAugust 17, 202633 changesAugust 10, 2026116 changesAugust 3, 202613 changes
›
Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated September 7, 2026

Smartest
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)Anthropic56.8Intelligence
Best open model
Kimi K3 (max)Kimi50.2Intelligence
Best value
Hy3-preview (Reasoning)Tencent268 pts/$Value
Best from China
Kimi K3 (max)Kimi50.2Intelligence
Top three by Intelligence
1Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)Anthropic56.8
2GPT-6 Astra (max)OpenAI54.7
3Claude Opus 5 (Adaptive Reasoning, Max Effort)Anthropic54.1
Top three open models
1Kimi K3 (max)Kimi · #8 overall50.2
2GLM-5.3 (max)Z AI · #9 overall48.6
3Qwen3.8 2.4T A95BAlibaba · #15 overall46.7
This week's changes
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)Intelligence · #1New
GPT-6 Astra (max)Intelligence · #2New
MAI-Image-2.6Image · #2New
Realtime TTS-2Speech · #2New
Muse Spark 1.3 (max)Intelligence · #5New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortIntelligenceValueSpeedLowest price
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1NewClaude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)ClosedAnthropic · 4 more variants56.8$2068272 s
2NewGPT-6 Astra (max)ClosedOpenAI · 5 more variants54.7$2064355 s
3▼ 2Claude Opus 5 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 4 more variants54.1$105695 s
4▼ 2Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)ClosedAnthropic53.2$206391 s
5NewMuse Spark 1.3 (max)ClosedMeta · 1 more variant53.0$2.023326 s
6▼ 3GPT-5.6 Sol (max)ClosedOpenAI · 5 more variants51.3$8.076256 s
7▼ 3Grok 4.6 (high)ClosedSpaceXAI · 3 more variants50.6$3.06040 s
8▼ 2Claude Opus 4.8 (Adaptive Reasoning, Max Effort)ClosedAnthropic47.8$105928 s
9NewGemini 3.8 Flash (high)ClosedGoogle · 2 more variants47.1$1.528111 s
10▼ 5Qwen3.8 MaxClosedAlibaba46.9$3.0402.4 s
11▼ 4Muse Spark 1.2 (xhigh)ClosedMeta46.8$2.026914 s
12▼ 4GPT-5.6 Terra (max)ClosedOpenAI · 5 more variants46.8$4.5114160 s
13▼ 4GPT-5.5 (xhigh)ClosedOpenAI · 4 more variants45.6$118582 s
14▼ 3Grok 4.5 (high)ClosedSpaceXAI45.5$3.05910 s
15▼ 5Gemini 3.7 Flash (high)ClosedGoogle · 2 more variants45.2$1.53059.5 s
16▼ 4Claude Sonnet 5 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant45.1$4.075185 s
17▼ 4Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant44.3$104814 s
18▼ 2GPT-5.6 Luna (max)ClosedOpenAI · 5 more variants43.4$0.45130136 s
19▼ 4GPT-5.4 (xhigh)ClosedOpenAI · 2 more variants42.8$5.6149123 s
20▼ 6Muse Spark 1.1 (xhigh)ClosedMeta41.2$2.0——
21▼ 2DeepSeek V4 Flash Vision (Reasoning, Max Effort)ClosedDeepSeek40.7$0.661231.0 s
22▼ 4Gemini 3.6 Flash (high)ClosedGoogle40.3$1.521815 s
23▼ 6Gemini 3.5 Flash (high)ClosedGoogle · 2 more variants39.7$3.421216 s
24▼ 4Agnes 2.5 Pro BetaClosedSapiens AI39.5$0.15——
25▼ 4Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 2 more variants38.5$6.059119 s
26▼ 2GPT-5.3 Codex (xhigh)ClosedOpenAI36.9$4.813760 s
27▼ 2Motif 3 (Beta)ClosedMotif Technologies36.8———
28▼ 6Gemini 3.1 Pro PreviewClosedGoogle36.7$4.511625 s
29▼ 6Qwen3.7 MaxClosedAlibaba36.6$3.81982.3 s
30▼ 4Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant36.4$104221 s
31▼ 4Muse SparkClosedMeta35.8———
32▼ 4GPT-5.2 (xhigh)ClosedOpenAI · 2 more variants35.0$4.883148 s
33NewApodex 1.1ClosedApodex34.9$0.98——
34NewQuasar 438B (max, based on GLM-5.2)ClosedMultiverse Computing34.2$0.901680.9 s
35▼ 6Claude Opus 4.5 (Reasoning)ClosedAnthropic · 1 more variant33.6$105617 s
36▼ 5MiMo-V2-ProClosedXiaomi33.1———
37▼ 5GPT-5.2 Codex (xhigh)ClosedOpenAI33.0$4.8——
38▼ 5Qwen3.6 Max PreviewClosedAlibaba32.9$2.9533.3 s
39▼ 9Solar Pro 4ClosedUpstage32.7$0.52842.0 s
40▼ 4Gemini 3 Pro Preview (high)ClosedGoogle · 1 more variant32.4$4.5——
41▼ 7GPT-5.4 mini (xhigh)ClosedOpenAI · 2 more variants31.9$1.715316 s
42▼ 2Qwen3.7 PlusClosedAlibaba31.9$0.70562.2 s
43▼ 5JT-4.1 Flash 236B A21BClosedChina Mobile31.8———
44▼ 9Grok Build 0.1 0616ClosedSpaceXAI31.7$1.3650.5 s
45▼ 8Qwen3.6 PlusClosedAlibaba31.5$1.1552.0 s
46▼ 5GLM-5-TurboClosedZ AI31.0———
47▼ 8GPT-5.4 nano (xhigh)ClosedOpenAI · 2 more variants30.9$0.4617815 s
48▼ 6Gemini 3 Flash Preview (Reasoning)ClosedGoogle · 1 more variant30.7$1.12175.6 s
49▼ 6Grok 4.20 0309 v2 (Reasoning)ClosedSpaceXAI · 1 more variant30.0$1.610724 s
50▼ 6Grok 4.3 (high)ClosedSpaceXAI · 3 more variants29.9$1.614118 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 “—”.