Skip to content
IFAI

Model rankings

1133 models · 5 boards · 2 sources

‹
Week of April 13, 2026
May 25, 202617 changesMay 18, 202616 changesMay 11, 202665 changesMay 4, 202616 changesApril 27, 202624 changesApril 20, 202627 changesApril 13, 202637 changesApril 6, 202641 changesMarch 30, 2026230 changesMarch 23, 202626 changesMarch 16, 202622 changesMarch 9, 202665 changes
›
Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated April 17, 2026

Smartest
Gemini 3.1 Pro PreviewGoogle57.2Intelligence
Best open model
GLM-5.1 (Reasoning)Z AI51.4Intelligence
Best value
Qwen3.5 0.8B (Reasoning)Alibaba526 pts/$Value
Best from China
GLM-5.1 (Reasoning)Z AI51.4Intelligence
Top three by Intelligence
1Gemini 3.1 Pro PreviewGoogle57.2
2GPT-5.4 (xhigh)OpenAI56.8
3GPT-5.3 Codex (xhigh)OpenAI53.6
Top three open models
1GLM-5.1 (Reasoning)Z AI · #7 overall51.4
2GLM-5 (Reasoning)Z AI · #10 overall49.8
3MiniMax-M2.7MiniMax · #12 overall49.6
This week's changes
claude-opus-4-7Coding · #1New
Gemini 3.1 Flash TTSSpeech · #2New
ImagineArt 2.0Image · #11New
AsyncFlow V2, asyncSpeech · #32New
Lightning v3.1Speech · #46New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortIntelligenceValueSpeedLowest price
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—Gemini 3.1 Pro PreviewClosedGoogle57.2$4.512929 s
2—GPT-5.4 (xhigh)ClosedOpenAI56.8$5.672206 s
3—GPT-5.3 Codex (xhigh)ClosedOpenAI53.6$4.881116 s
4—Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic53.0$104017 s
5—Muse SparkClosedMeta52.2———
6—Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic51.7$6.04894 s
7—GLM-5.1 (Reasoning)OpenZ AI51.4$2.2401.6 s
8—GPT-5.2 (xhigh)ClosedOpenAI51.3$4.869173 s
9—Qwen3.6 PlusClosedAlibaba50.0$1.1532.8 s
10—GLM-5 (Reasoning)OpenZ AI49.8$1.6631.7 s
11—Claude Opus 4.5 (Reasoning)ClosedAnthropic49.7$104514 s
12—MiniMax-M2.7OpenMiniMax49.6$0.52402.4 s
13—Grok 4.20 0309 v2 (Reasoning)ClosedxAI49.3$3.016213 s
14—MiMo-V2-ProClosedXiaomi49.2$1.5663.0 s
15—GPT-5.2 Codex (xhigh)ClosedOpenAI49.0$4.8121125 s
16—GPT-5.4 mini (xhigh)ClosedOpenAI48.9$1.71499.8 s
17—Grok 4.20 0309 (Reasoning)ClosedxAI48.5$3.015517 s
18—Gemini 3 Pro Preview (high)ClosedGoogle48.4$4.513033 s
19—GPT-5.1 (high)ClosedOpenAI47.7$3.49130 s
20—Kimi K2.5 (Reasoning)OpenKimi46.8$1.2352.3 s
21—GLM-5-TurboClosedZ AI46.8———
22—GPT-5.2 (medium)ClosedOpenAI46.6$4.8——
23—Claude Opus 4.6 (Non-reasoning, High Effort)ClosedAnthropic46.5$10371.7 s
24—Gemini 3 Flash Preview (Reasoning)ClosedGoogle46.4$1.11497.3 s
25—Qwen3.5 397B A17B (Reasoning)OpenAlibaba45.1$1.4532.6 s
26—MiMo-V2-Omni-0327ClosedXiaomi44.9———
27—GPT-5 (high)ClosedOpenAI44.6$3.48584 s
27—GPT-5 Codex (high)ClosedOpenAI44.6$3.416810 s
29—Claude Sonnet 4.6 (Non-reasoning, High Effort)ClosedAnthropic44.4$6.0441.3 s
30—GPT-5.4 nano (xhigh)ClosedOpenAI44.0$0.461564.4 s
31—GLM-5.1 (Non-reasoning)OpenZ AI43.8$2.2422.2 s
32—MiMo-V2-OmniClosedXiaomi43.4———
33—GPT-5.1 Codex (high)ClosedOpenAI43.1$3.41638.2 s
34—Claude Opus 4.5 (Non-reasoning)ClosedAnthropic43.1$10451.5 s
35—Claude 4.5 Sonnet (Reasoning)ClosedAnthropic43.0$6.0409.9 s
36—GLM 5V Turbo (Reasoning)ClosedZ AI42.9———
37—Claude Sonnet 4.6 (Non-reasoning, Low Effort)ClosedAnthropic42.6$6.0451.3 s
38—GLM-4.7 (Reasoning)OpenZ AI42.1$1.01071.1 s
39—Qwen3.5 27B (Reasoning)OpenAlibaba42.1$0.83855.7 s
40—GPT-5 (medium)ClosedOpenAI42.0$3.47644 s
41—Claude 4.1 Opus (Reasoning)ClosedAnthropic42.0$30309.9 s
42—MiniMax-M2.5OpenMiniMax41.9$0.52582.1 s
43—DeepSeek V3.2 (Reasoning)OpenDeepSeek41.7$0.32311.9 s
44—Qwen3.5 122B A10B (Reasoning)OpenAlibaba41.6$1.11312.5 s
45—Grok 4ClosedxAI41.5$6.05511 s
46—MiMo-V2-Flash (Feb 2026)OpenXiaomi41.5$0.151202.5 s
47—Gemini 3 Pro Preview (low)ClosedGoogle41.3$4.5——
48—GPT-5 mini (high)ClosedOpenAI41.2$0.697795 s
49—Kimi K2 ThinkingOpenKimi40.9$1.1881.4 s
50—o3-proClosedOpenAI40.7$3527128 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 “—”.