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
1—Qwen3.8 Max (0902)ClosedAlibaba · 1 more variant45.4$3.0393.0 s
2—Step 5 PreviewClosedStepFun43.7$1.4793.0 s
3—DeepSeek V4 Flash Vision (Reasoning, Max Effort)ClosedDeepSeek34.8$0.662271.1 s
4—Qwen3.7 MaxClosedAlibaba29.5$3.82122.3 s
5—MiMo-V2-ProClosedXiaomi28.6———
6—Qwen3.6 Max PreviewClosedAlibaba28.4$2.9773.0 s
7—Qwen3.6 PlusClosedAlibaba27.0$1.1572.0 s
8—GLM-5-TurboClosedZ AI26.6———
9—Qwen3.7 PlusClosedAlibaba25.2$0.70712.2 s
10—MiMo-V2-Omni-0327ClosedXiaomi · 1 more variant25.1———
11—GLM 5V Turbo (Reasoning)ClosedZ AI23.5———
12—Qwen3 Max ThinkingClosedAlibaba · 1 more variant21.3———
13—Qwen3.5 Omni PlusClosedAlibaba20.4$1.51042.2 s
14—Step 3.5 Flash 2603ClosedStepFun17.0$0.151353.3 s
15—Doubao Seed CodeClosedByteDance Seed16.9———
16—Qwen3 MaxClosedAlibaba · 1 more variant15.6$2.4562.2 s
17—ERNIE 5.0 Thinking PreviewClosedBaidu14.3———
18—Qwen3.5 Omni FlashClosedAlibaba12.5$0.282451.9 s
19—Qwen2.5 MaxClosedAlibaba8.0———
20—Qwen2.5 TurboClosedAlibaba6.4$0.0881062.2 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 “—”.