Skip to content
IFAI

Model rankings

1319 models · 5 boards · 2 sources

‹
Week of June 29, 2026
August 10, 2026116 changesAugust 3, 202613 changesJuly 27, 202639 changesJuly 20, 202618 changesJuly 13, 202611 changesJuly 6, 202626 changesJune 29, 202641 changesJune 22, 202612 changesJune 15, 2026184 changesJune 8, 202624 changesJune 1, 202622 changesMay 25, 202617 changes
›
Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated July 3, 2026

Smartest
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic59.9Intelligence
Best open model
GLM-5.2 (max)Z AI51.1Intelligence
Best value
HyperNova 60B 2605Multiverse Computing341 pts/$Value
Best from China
GLM-5.2 (max)Z AI51.1Intelligence
Top three by Intelligence
1Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic59.9
2Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic55.7
3GPT-5.5 (xhigh)OpenAI54.8
Top three open models
1GLM-5.2 (max)Z AI · #7 overall51.1
2MiniMax-M3MiniMax · #12 overall44.4
3DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek · #13 overall44.3
This week's changes
Reve 2.0Image · #2New
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)Intelligence · #5New
claude-sonnet-5-thinkingCoding · #5New
Fish Audio S2.1 ProSpeech · #15New
OpenAudio S1 MiniSpeech · #50New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortIntelligenceValueSpeedLowest price
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)ClosedAnthropic59.9$2073173 s
2—Claude Opus 4.8 (Adaptive Reasoning, Max Effort)ClosedAnthropic55.7$106840 s
3—GPT-5.5 (xhigh)ClosedOpenAI54.8$117184 s
4—Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic53.5$105218 s
5NewClaude Sonnet 5 (Adaptive Reasoning, Max Effort)ClosedAnthropic53.4$6.079163 s
6▼ 1GPT-5.5 (high)ClosedOpenAI53.1$116746 s
7▼ 1GPT-5.4 (xhigh)ClosedOpenAI51.4$5.6138124 s
8▼ 1GPT-5.5 (medium)ClosedOpenAI50.4$11679.7 s
9▼ 1Gemini 3.5 Flash (high)ClosedGoogle50.2$3.417420 s
10▼ 1Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic47.2$6.048104 s
11▼ 1Gemini 3.1 Pro PreviewClosedGoogle46.5$4.513122 s
12▼ 1Qwen3.7 MaxClosedAlibaba46.0$3.81992.5 s
13▼ 1Gemini 3.5 Flash (medium)ClosedGoogle45.4$3.417316 s
14▼ 1GPT-5.3 Codex (xhigh)ClosedOpenAI44.3$4.888125 s
15▼ 1Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic43.7$104018 s
16▼ 1GPT-5.5 (low)ClosedOpenAI43.5$11691.9 s
17▼ 1Muse SparkClosedMeta43.1———
18▼ 1Claude Opus 4.7 (Non-reasoning, High Effort)ClosedAnthropic42.7$10441.5 s
19▼ 1GPT-5.2 (xhigh)ClosedOpenAI42.2$4.875158 s
20NewClaude Sonnet 5 (Non-reasoning, High Effort)ClosedAnthropic41.7$6.0621.3 s
21▼ 2Claude Opus 4.5 (Reasoning)ClosedAnthropic40.8$105417 s
22▼ 2MiMo-V2-ProClosedXiaomi40.3$1.5——
23▼ 2GPT-5.2 Codex (xhigh)ClosedOpenAI40.1$4.816238 s
24▼ 2Qwen3.6 Max PreviewClosedAlibaba40.0$2.9423.3 s
25▼ 2GPT-5.4 mini (xhigh)ClosedOpenAI40.0$1.71655.3 s
26▼ 2Grok Build 0.1 0616ClosedxAI39.8$1.3790.5 s
27▼ 2Qwen3.6 PlusClosedAlibaba39.6$1.1512.9 s
28▼ 2Gemini 3 Pro Preview (high)ClosedGoogle39.6$4.5——
29▼ 2GPT-5.4 (low)ClosedOpenAI39.1$5.61001.7 s
30▼ 2Qwen3.7 PlusClosedAlibaba39.0$0.59503.0 s
31▼ 1GPT-5.4 nano (xhigh)ClosedOpenAI38.2$0.461425.8 s
32▼ 1GLM-5-TurboClosedZ AI38.1———
33▼ 1GPT-5.2 (medium)ClosedOpenAI38.0$4.8——
34▼ 1Claude Opus 4.6 (Non-reasoning, High Effort)ClosedAnthropic37.8$10382.7 s
35▼ 1Gemini 3 Flash Preview (Reasoning)ClosedGoogle37.8$1.11747.2 s
36▼ 1Grok 4.3 (high)ClosedxAI37.6$1.612819 s
37▼ 1Grok 4.20 0309 v2 (Reasoning)ClosedxAI37.0$3.022911 s
38▼ 9GPT-5.1 (high)ClosedOpenAI36.9$3.49363 s
39▼ 2Grok 4.20 0309 (Reasoning)ClosedxAI36.5$3.0——
40▲ 9Claude 4.5 Sonnet (Reasoning)ClosedAnthropic36.4$6.04812 s
41▼ 3MiMo-V2-Omni-0327ClosedXiaomi36.4$0.80——
42▼ 3GPT-5 Codex (high)ClosedOpenAI36.1$3.41498.4 s
43▼ 3GPT-5 (high)ClosedOpenAI36.1$3.48786 s
44▼ 3Grok 4.3 (medium)ClosedxAI36.0$1.610912 s
45▼ 3Claude Sonnet 4.6 (Non-reasoning, High Effort)ClosedAnthropic35.9$6.0451.2 s
46▼ 3Grok 4.3 (low)ClosedxAI35.4$1.61225.6 s
47▼ 3GPT-5.5 (Non-reasoning)ClosedOpenAI35.4$11621.0 s
48▼ 3MiMo-V2-OmniClosedXiaomi35.0$0.000——
49▼ 3Gemini 3.5 Flash (minimal)ClosedGoogle34.9$3.41640.9 s
50▼ 3GPT-5.1 Codex (high)ClosedOpenAI34.7$3.41666.1 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 “—”.