Skip to content
IFAI

Model rankings

896 models · 5 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated November 11, 2026

Smartest
Best open model
Kimi K3.1 ProKimi46.5Intelligence
Best value
Claude Haiku 5.5 (Max)Anthropic183 pts/$Value
Best from China
Kimi K3.1 ProKimi46.5Intelligence
Top three open models
1Kimi K3.1 ProKimi · #11 overall46.5
2GLM-5.3 (Max)Z AI · #23 overall31.7
3MiMo-V2.6-ProXiaomi · #27 overall29.9
This week's changes
Simba 3.5Speech · #5New
Bach 1.0 ProVideo · #7New
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1NewClaude Fable 5.2 (Max, Default Fallback)Anthropic · 4 more variants64.6$1695253 s
2▼ 1Gemini 4 Carbon (High)ClosedGoogle · 2 more variants60.0$8.0108101 s
3▼ 1Claude Opus 5.5 (Max, Default Fallback)ClosedAnthropic · 4 more variants59.1$8.095688 s
4▼ 1GPT-6 Astra (Max)ClosedOpenAI · 4 more variants56.9$2050300 s
5▼ 1GPT-6.1 Sol (Max)ClosedOpenAI · 4 more variants54.6$4.070309 s
6▼ 1Claude Sonnet 5.5 (Max, Default Fallback)ClosedAnthropic · 4 more variants54.5$4.0129537 s
7▼ 1GPT-6.1 Terra (Max)ClosedOpenAI · 5 more variants51.3$2.098310 s
8▼ 1Gemini 4 Argon (High)ClosedGoogle50.4$8.09550 s
9▼ 1Muse Wonder Full (Max)ClosedMeta50.1———
10▼ 1Claude Fable 5.1 (Xhigh, Default Fallback)ClosedAnthropic · 4 more variants50.0$2060102 s
11NewClaude Opus 5 (Max)ClosedAnthropic44.2$105464 s
11NewGPT-6 Sol (Max)ClosedOpenAI44.2$4.0165110 s
13▼ 3Muse Wonder (Max)ClosedMeta · 1 more variant43.6$8.013738 s
14NewMuse Spark 1.3 (Max)ClosedMeta36.6$2.017536 s
15▼ 4Claude Haiku 5.5 (Max)ClosedAnthropic · 4 more variants36.5$0.20232369 s
16NewMuse Ember (Max)ClosedMeta · 1 more variant36.0$0.207856.5 s
17NewGPT-5.6 Terra (Max)ClosedOpenAI32.3$4.5134109 s
18▼ 6Gemini 3.8 Flash (High)ClosedGoogle · 2 more variants30.8$1.512926 s
19NewInkling 2 SmallClosedThinking Machines30.6$0.481112.4 s
20▼ 7GPT-6 Luna (Max)ClosedOpenAI · 5 more variants27.9$0.20127114 s
21▼ 7Muse Spark Open (Xhigh)OpenMeta24.9$2.02300.8 s
22NewGPT-5.6 Luna (Max)ClosedOpenAI23.8$0.45129130 s
23▼ 8Nemotron 3.5 Super VLNVIDIA13.6$0.262930.9 s
24▼ 8Inkling SmallOpenThinking Machines12.9$0.521002.1 s
25▼ 8Inkling (Xhigh)OpenThinking Machines12.5$1.81932.2 s
26▼ 8Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA11.8$1.12521.1 s
27▼ 8Gemini 3.5 Flash-LiteClosedGoogle11.7$0.854577.0 s
28NewClaude 4.5 Haiku (Reasoning)ClosedAnthropic7.4$2.09423 s
29▼ 9Muse Glimmer (High)OpenMeta6.3$0.521070.8 s
30NewGemini 3.1 Flash-LiteClosedGoogle6.2$0.563514.7 s
31▼ 10Nemotron 3.5 LightningNVIDIA5.5$0.0952760.5 s
32▼ 10Granite 4.2 8BOpenIBM5.1$0.111340.9 s
33▼ 10Granite 4.2 3BOpenIBM4.7———
34NewGemma 4 31B (Reasoning)OpenGoogle4.4$0.000351.1 s
35Newgpt-oss-120b (High)OpenOpenAI3.8$0.262060.8 s
36▼ 12NVIDIA Nemotron 3 Nano 4BNVIDIA1.8———

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 “—”.

This week uses version 5 of the Intelligence Index; scores from different versions are not comparable.