Skip to content
IFAI

Model rankings

1037 models · 5 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated October 19, 2026

Smartest
Claude Opus 5.5 (Max, Default Fallback)Anthropic57.6Intelligence
Best open model
MiMo-V2.6-ProXiaomi46.3Intelligence
Best value
Agnes 2.5 Pro BetaSapiens AI235 pts/$Value
Best from China
MiMo-V2.6-ProXiaomi46.3Intelligence
Top three open models
1MiMo-V2.6-ProXiaomi · #11 overall46.3
2GLM-5.3 (Max)Z AI · #13 overall44.8
3Step 5 PreviewStepFun · #14 overall43.7
This week's changes
Muse Wonder Full (Max)Intelligence · #3New
FLUX 3 Max (720p)Video · #4New
Muse Wonder Full (Max)Coding · #6New
Muse Wonder (Max)Intelligence · #7New
Kimi K3.1 Pro (Max)Coding · #7New
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—MiMo-V2.6-ProOpenXiaomi46.3$0.54514.0 s
2—GLM-5.3 (Max)OpenZ AI · 1 more variant44.8$2.2952.5 s
3NewStep 5 PreviewOpenStepFun43.7$1.4942.2 s
4▼ 1Kimi K3 (Max)OpenKimi · 1 more variant43.6$6.0443.5 s
5▼ 1GLM-5.3-FlashOpenZ AI41.8$0.24782.6 s
6NewLing 3.1 FlashOpenInclusionAI41.1$0.452111.9 s
7▼ 2Qwen3.8 2.4T A95BOpenAlibaba39.9$3.0383.1 s
8▼ 2Qwen3.8-Flash-NextOpenAlibaba39.8$0.23522.0 s
9▼ 2DeepSeek V4.1 Flash (Max)OpenDeepSeek · 1 more variant39.5$0.522320.9 s
10NewMuse Spark Open (Xhigh)OpenMeta38.9$2.01410.8 s
11▼ 3MiMo-V2.6-FlashOpenXiaomi37.9$0.18516.4 s
12▼ 3DeepSeek V4 Pro 0813 (Max)OpenDeepSeek · 1 more variant36.0$2.01101.6 s
13▼ 1Qwen3.8 27B (Xhigh)OpenAlibaba · 3 more variants33.7$1.1444.0 s
14▼ 1Motif 3OpenMotif Technologies33.6———
15▼ 1K2 Horizon 375B A23BOpenInstitute of Foundation Models30.5$0.0001,0632.3 s
16NewBeam 1.0OpenReflection30.3$1.03250.8 s
17▼ 2MiniMax-M3OpenMiniMax29.2$0.521231.0 s
18▼ 2Nex-N2-Pro (Based on Qwen3.5-397B-A17B)OpenNex AGI28.2———
19NewNemotron 3.5 Super VLOpenNVIDIA26.5$0.314220.8 s
20▲ 1Kimi K2.7 CodeOpenKimi25.8$1.7572.9 s
21▲ 1Inkling SmallOpenThinking Machines25.7$0.521992.1 s
22▲ 1K2 Horizon MoVA 36B A4BOpenInstitute of Foundation Models25.3———
23▲ 1Hy3OpenTencent25.3$0.24862.9 s
24▲ 2Inkling (Xhigh)OpenThinking Machines25.0$1.82161.8 s
25▲ 2Solar Open2 250BOpenUpstage24.7———
26▲ 2Ling-3.0-flash-VLOpenInclusionAI24.6———
27▲ 3Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA22.9$1.11441.2 s
28▲ 7Ling-3.0-flash-FinOpenInclusionAI22.6$0.113211.7 s
29▲ 10G9v3-39A5BOpenAI9Stars21.8———
30▲ 11A.X-K2OpenSK Telecom21.5———
31▲ 11Qwen3.5 397B A17B (Non-reasoning)OpenAlibaba · 1 more variant21.4$1.4572.2 s
32NewNemotron 3.5 Bolt 74B-A9BOpenNVIDIA21.4———
33▲ 12K2 Horizon 7BOpenInstitute of Foundation Models20.6———
34▲ 13K-EXAONE 2.0 0803OpenLG AI Research19.7———
35▲ 15LongCat 2.0OpenLongCat19.1$1.3672.8 s
36▲ 17Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant18.2$0.841392.0 s
37▲ 17Qwen3.5 122B A10B (Non-reasoning)OpenAlibaba · 1 more variant17.7$1.11432.3 s
38▲ 17Muse Glimmer (High)OpenMeta17.5$0.521430.9 s
39▲ 18Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant16.7$0.17711.0 s
40▲ 18Ring-2.6-1TOpenInclusionAI16.6$0.851263.9 s
41▲ 20K2 Horizon 3.7BOpenInstitute of Foundation Models15.6———
42▲ 23Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant14.7$0.000361.1 s
43▲ 25Mistral Medium 3.5OpenMistral14.2$3.01602.4 s
44▲ 25Gemma 4 12B (Reasoning)OpenGoogle · 1 more variant14.2$0.151192.3 s
45▲ 28Apriel-v1.6-15B-ThinkerOpenServiceNow13.4———
46▲ 28Qwen3.5 9B (Non-reasoning)OpenAlibaba · 1 more variant13.3$0.191140.7 s
47▲ 28EXAONE 4.5 33B (Reasoning)OpenLG AI Research13.2———
48▲ 28Command A+OpenCohere · 1 more variant13.1$0.0001580.5 s
49▲ 28Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant13.1$0.060120.9 s
50▲ 29Nemotron 3.5 LightningOpenNVIDIA12.9$0.0952980.5 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 “—”.