Skip to content
IFAI

Model rankings

1539 models · 5 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated September 28, 2026

Best open model
MiMo-V2.6-ProXiaomi46.3Intelligence
Best value
Llama 3.1 Instruct 8BMeta252 pts/$Value
Best from China
MiMo-V2.6-ProXiaomi46.3Intelligence
Top three open models
1MiMo-V2.6-ProXiaomi · #10 overall46.3
2GLM-5.3 (max)Z AI · #12 overall44.8
3Kimi K3 (max)Kimi · #15 overall43.6
This week's changes
Eleven v4Speech · #1New
Qwen-Audio-3.1-TTS-PlusSpeech · #2New
claude-sonnet-5.5-xhighCoding · #3New
gpt-6.1-sol-maxCoding · #4New
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1NewMiMo-V2.6-ProOpenXiaomi46.3$0.54443.8 s
2▼ 1Qwen3.8 Max (0902)ClosedAlibaba45.4$3.0393.0 s
3▼ 1GLM-5.3 (max)OpenZ AI44.8$2.2912.6 s
4▼ 1Step 5 PreviewClosedStepFun43.7$1.4793.0 s
5▼ 1Kimi K3 (max)OpenKimi43.6$6.0——
6▼ 1GLM 5.3 FlashOpenZ AI41.8$0.24543.2 s
7▼ 1Qwen3.8 MaxClosedAlibaba40.2$3.0373.0 s
8▼ 1Qwen3.8 2.4T A95BOpenAlibaba39.9$3.0383.1 s
9▼ 1Qwen3.8-Flash-NextOpenAlibaba39.8$0.23582.6 s
10▼ 1DeepSeek V4.1 Flash (Reasoning, Max Effort)OpenDeepSeek39.5$0.522201.2 s
11NewMiMo-V2.6-FlashOpenXiaomi37.9$0.18593.5 s
12▼ 2DeepSeek V4 Pro 0813 (Reasoning, Max Effort)OpenDeepSeek36.0$2.01041.6 s
13▼ 2DeepSeek V4 Flash Vision (Reasoning, Max Effort)ClosedDeepSeek34.8$0.662271.1 s
14▼ 2Kimi K3 (low)OpenKimi34.5$6.0——
15▼ 2DeepSeek V4 Flash 0731 (Reasoning, Max Effort)OpenDeepSeek34.3$0.662291.1 s
16NewGLM-5.3 (low)OpenZ AI34.3$2.2843.0 s
17▼ 3GLM-5.2 (max)OpenZ AI33.7$2.2843.2 s
18▼ 3Qwen3.8 27B (xhigh)OpenAlibaba33.7$1.1473.8 s
19▼ 3DeepSeek V4 Pro 0424 (Reasoning, Max Effort)OpenDeepSeek30.4$0.541111.5 s
20▼ 3DeepSeek V4 Pro 0424 (Reasoning, High Effort)OpenDeepSeek30.1$0.541041.8 s
21▼ 3Qwen3.7 MaxClosedAlibaba29.5$3.82122.3 s
22▼ 3MiniMax-M3OpenMiniMax29.2$0.521751.1 s
23▼ 3MiMo-V2-ProClosedXiaomi28.6———
24▼ 3Qwen3.6 Max PreviewClosedAlibaba28.4$2.9773.0 s
25▼ 3GLM-5 (Reasoning)OpenZ AI27.9$1.6851.5 s
26▼ 3Qwen3.8 27B (medium)OpenAlibaba27.6$1.1563.8 s
27▼ 3Qwen3.6 PlusClosedAlibaba27.0$1.1572.0 s
28▼ 3Kimi K2.6OpenKimi27.0$1.7——
29▼ 3GLM-5-TurboClosedZ AI26.6———
30▼ 3Qwen3.8 27B (low)OpenAlibaba26.2$1.1573.8 s
31▼ 3GLM-5.1 (Reasoning)OpenZ AI26.1$2.0751.7 s
32▼ 3DeepSeek V4 Flash 0420 (Reasoning, High Effort)OpenDeepSeek26.0$0.17——
33▼ 3MiMo-V2.5-ProOpenXiaomi26.0$0.54382.3 s
34▼ 3Kimi K2.7 CodeOpenKimi25.8$1.7——
35▼ 3Hy3OpenTencent25.3$0.25873.0 s
36▼ 3MiMo-V2.5OpenXiaomi25.2$0.184626 s
37▼ 3Qwen3.7 PlusClosedAlibaba25.2$0.70712.2 s
38▼ 3MiMo-V2-Omni-0327ClosedXiaomi25.1———
39▼ 3Ling 3.0 FlashOpenInclusionAI24.9$0.113683.0 s
40NewDeepSeek V4.1 Flash (Non-Reasoning)OpenDeepSeek24.7$0.522391.1 s
41▼ 4Ling-3.0-flash-VLOpenInclusionAI24.6$0.111451.9 s
42▼ 4GLM-5.1 (Non-reasoning)OpenZ AI24.2$2.1711.7 s
43▼ 4DeepSeek V4 Flash 0420 (Reasoning, Max Effort)OpenDeepSeek24.2$0.17——
44▼ 4MiMo-V2-OmniClosedXiaomi23.9———
45▼ 4Kimi K2.6 (Non-reasoning)OpenKimi23.6$1.7——
46▼ 4GLM 5V Turbo (Reasoning)ClosedZ AI23.5———
47▼ 4Kimi K2.5 (Reasoning)OpenKimi23.5$1.1——
48▼ 4Qwen3.5 27B (Reasoning)OpenAlibaba22.9$0.83795.6 s
49▼ 4MiniMax-M2.5OpenMiniMax22.8$0.52971.5 s
50▼ 4MiniMax-M2.7OpenMiniMax22.8$0.52681.6 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 “—”.