Skip to content
IFAI

Model rankings

1388 models · 5 boards · 2 sources

‹
Week of July 27, 2026
September 7, 2026144 changesAugust 31, 202620 changesAugust 24, 202615 changesAugust 17, 202633 changesAugust 10, 2026116 changesAugust 3, 202613 changesJuly 27, 202639 changesJuly 20, 202618 changesJuly 13, 202611 changesJuly 6, 202626 changesJune 29, 202641 changesJune 22, 202612 changes
›
Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published August 2, 2026

Most preferred
claude-fable-5Anthropic1,509Score
Best open model
kimi-k3-maxMoonshot AI1,485Score
Best from China
qwen3.8-maxAlibaba1,496Score
Most voted
claude-3-opus-20240229Anthropic194,909Votes
Top three by Score
1claude-fable-5Anthropic1,509
2claude-opus-4-6-thinkingAnthropic1,505
3claude-opus-4-7-thinkingAnthropic1,502
Top three open models
1kimi-k3-maxMoonshot AI · #11 overall1,485
2glm-5.2-maxZ.ai · #29 overall1,469
3glm-5.1Z.ai · #32 overall1,469
This week's changes
Claude Opus 5 (Adaptive Reasoning, Max Effort)Intelligence · #1New
claude-opus-5-maxCoding · #1New
Reve 2.1Image · #2New
MiniMax H3Video · #2New
qwen3.8-maxCoding · #4New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortScoreLowest price
RankChangeModelScore95% intervalVotesPrice $/M
1—claude-fable-5ClosedAnthropic1,509±617,799—
2—claude-opus-4-6-thinkingClosedAnthropic · 1 more variant1,505±467,203—
3—claude-opus-4-7-thinkingClosedAnthropic · 1 more variant1,502±454,781—
4—claude-opus-5-highClosedAnthropic1,492±610,704—
5Newclaude-opus-5-maxClosedAnthropic1,490±95,124—
6▼ 1muse-spark-1.1ClosedMeta1,490±612,086—
7▼ 1muse-sparkClosedMeta1,488±613,486—
8—gemini-3-proClosedGoogle1,486±441,241—
9▼ 2gemini-3.1-pro-previewClosedGoogle1,485±389,133—
10—claude-opus-4-8-thinkingClosedAnthropic · 1 more variant1,484±535,303—
11▼ 2gpt-5.6-sol-xhighClosedOpenAI1,483±610,716—
12▼ 1gemini-3.6-flashClosedGoogle1,483±78,575—
13▼ 1gpt-5.5-highClosedOpenAI1,482±449,978—
14▼ 1gpt-5.4-highClosedOpenAI1,477±460,264—
15▼ 1gemini-3.5-flash-highClosedGoogle1,476±710,006—
16—gpt-5.5ClosedOpenAI1,476±451,172—
17▼ 2gpt-5.2-chat-latest-20260210ClosedOpenAI1,476±434,036—
18▼ 1grok-4.20-beta1ClosedxAI1,474±526,576—
19▲ 4gemini-3.5-flash-mediumClosedGoogle1,474±518,778—
20▼ 2gpt-5.5-instantClosedOpenAI1,473±525,680—
21▼ 2gemini-3-flashClosedGoogle · 1 more variant1,473±430,635—
22▼ 2claude-opus-4-5-20251101-thinking-32kClosedAnthropic1,473±436,973—
23▼ 2grok-4.20-beta-0309-reasoningClosedxAI1,472±461,765—
24▼ 2claude-sonnet-4-6ClosedAnthropic1,472±461,253—
25▼ 1grok-4.20-multi-agent-beta-0309ClosedxAI1,471±460,405—
26▼ 1claude-opus-4-5-20251101ClosedAnthropic1,469±370,544—
27▼ 1grok-4.5ClosedxAI1,469±612,507—
28Newgpt-5.6-terra-xhighClosedOpenAI1,468±611,082—
29▼ 2grok-4.1-thinkingClosedxAI · 1 more variant1,466±365,089—
30▼ 2gpt-5.4ClosedOpenAI1,465±463,185—
31▼ 2claude-sonnet-5-highClosedAnthropic1,462±618,078—
32▼ 2gemini-3.5-flash-liteClosedGoogle1,457±78,488$0.85
33▼ 2claude-sonnet-4-5-20250929-thinking-32kClosedAnthropic1,456±381,922—
34▼ 2claude-sonnet-4-5-20250929ClosedAnthropic1,455±380,326—
35▼ 2gpt-5.1-highClosedOpenAI1,455±440,687—
36▼ 2gemma-4-31bOpenGoogle1,451±85,844$0.000
37Newgpt-5.6-luna-xhighClosedOpenAI1,450±611,383—
38▼ 3claude-opus-4-1-20250805-thinking-16kClosedAnthropic1,449±349,738—
39▼ 2gpt-5.3-chat-latestClosedOpenAI1,449±432,598—
40▼ 4gpt-5.4-mini-highClosedOpenAI1,449±459,046—
41▼ 3claude-opus-4-1-20250805ClosedAnthropic1,447±377,219—
42▼ 3gemini-2.5-proClosedGoogle1,446±2124,056—
43▼ 3gpt-4.5-preview-2025-02-27ClosedOpenAI1,445±614,547—
44▼ 3chatgpt-4o-latest-20250326ClosedOpenAI1,443±382,359—
45▼ 3grok-4.3ClosedxAI1,442±450,862—
46▼ 3inklingOpenThinking Machines1,441±69,873$1.8
47▼ 3gpt-5.1ClosedOpenAI1,439±443,323—
48▼ 3gemma-4-26b-a4bOpenGoogle1,438±85,757—
49▼ 3gpt-5.2-highClosedOpenAI1,437±447,657—
50▼ 3gpt-5.2ClosedOpenAI1,435±378,761—

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 “—”.