Skip to content
IFAI

Model rankings

1447 models · 5 boards · 2 sources

‹
Week of August 24, 2026
October 5, 202634 changesSeptember 28, 202617 changesSeptember 21, 2026115 changesSeptember 14, 2026174 changesSeptember 7, 2026144 changesAugust 31, 202620 changesAugust 24, 202615 changesAugust 17, 202633 changesAugust 10, 2026116 changesAugust 3, 202613 changesJuly 27, 202639 changesJuly 20, 202618 changes
›
Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published August 27, 2026

Most preferred
claude-fable-5Anthropic1,507Score
Best open model
kimi-k3-maxMoonshot AI1,489Score
Best from China
kimi-k3-maxMoonshot AI1,489Score
Most voted
claude-3-opus-20240229Anthropic194,909Votes
Top three by Score
1claude-fable-5Anthropic1,507
2claude-opus-4-6-highAnthropic1,505
3claude-opus-4-7-highAnthropic1,502
Top three open models
1kimi-k3-maxMoonshot AI · #10 overall1,489
2glm-5.3-maxZ.ai · #15 overall1,484
3glm-5.2-maxZ.ai · #33 overall1,472
This week's changes
hy4-previewCoding · #5New
GLM-5.3 (max)Intelligence · #6New
MAI-Image-2.5-ProImage · #7New
qwen3.8-flash-nextCoding · #8New
glm-5.3-flashCoding · #11New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortScoreLowest price
RankChangeModelScore95% intervalVotesPrice $/M
1—claude-fable-5ClosedAnthropic1,507±525,824—
2—claude-opus-4-6-highClosedAnthropic1,505±472,104—
3—claude-opus-4-7-highClosedAnthropic1,502±460,136—
4—muse-spark-1.2 (xHigh)ClosedMeta1,498±103,247—
5—claude-opus-4-6ClosedAnthropic1,497±376,079—
6—claude-opus-4-7ClosedAnthropic1,494±461,282—
7—claude-opus-5-highClosedAnthropic1,492±531,570—
8—muse-spark-1.1ClosedMeta1,490±522,215—
9—gemini-3.7-flash-highClosedGoogle1,490±85,720—
10—muse-sparkClosedMeta1,488±613,574—
11—claude-opus-5-maxClosedAnthropic1,488±615,398—
12—gemini-3.1-pro-previewClosedGoogle1,487±3101,163—
13—gemini-3-proClosedGoogle1,486±440,674—
14▲ 1gpt-5.5-highClosedOpenAI1,482±461,604—
15▼ 1gpt-5.6-sol-xhighClosedOpenAI1,482±521,537—
16—claude-opus-4-8-highClosedAnthropic1,481±446,773—
17▲ 1gemini-3.6-flash-highClosedGoogle1,481±520,190—
18▼ 1qwen3.8-maxClosedAlibaba1,479±611,780$3.0
19—gemini-3.5-flash-highClosedGoogle1,479±432,174—
20▲ 1gpt-5.5ClosedOpenAI1,477±462,975—
21▼ 1gpt-5.4-highClosedOpenAI1,477±460,614—
22—gpt-5.2-chat-latest-20260210ClosedOpenAI1,476±434,229—
23—grok-4.20-beta1ClosedxAI1,475±526,645—
24▲ 4gemini-3-flashClosedGoogle · 1 more variant1,474±430,242—
25—qwen3.7-max-previewClosedAlibaba1,474±103,712—
26▼ 2gemini-3.5-flash-mediumClosedGoogle1,473±530,593—
27▼ 1gpt-5.5-instantClosedOpenAI1,473±525,857—
28▲ 1claude-opus-4-5-20251101-high-32kClosedAnthropic1,473±436,267—
29▼ 2claude-opus-4-8ClosedAnthropic1,473±447,459—
30—claude-sonnet-4-6ClosedAnthropic1,472±466,354—
31—grok-4.20-beta-0309-reasoningClosedxAI1,472±462,244—
32▲ 1grok-4.20-multi-agent-beta-0309ClosedxAI1,470±460,845—
33▼ 1grok-4.5ClosedxAI1,470±524,152—
34—claude-opus-4-5-20251101ClosedAnthropic1,469±370,044—
35—ernie-5.1ClosedBaidu1,468±537,102—
36▲ 3gpt-5.6-terra-xhighClosedOpenAI1,466±522,345—
37▼ 1gpt-5.4ClosedOpenAI1,466±463,594—
38—qwen3.5-max-previewClosedAlibaba1,465±521,478—
39▼ 2grok-4.1-thinkingClosedxAI · 1 more variant1,465±364,196—
40—claude-sonnet-5-highClosedAnthropic1,461±529,477—
41—grok-4.6-highClosedxAI1,461±103,471—
42—qwen3.6-max-previewClosedAlibaba1,460±85,198—
43▲ 1gemini-3.5-flash-liteClosedGoogle1,458±520,133$0.85
44▼ 1qwen3.7-plusClosedAlibaba1,456±536,304—
45▲ 1claude-sonnet-4-5-20250929-high-32kClosedAnthropic1,456±381,027—
46▼ 1dola-seed-2.0-proClosedByteDance1,456±374,258—
47▲ 1gpt-5.1-highClosedOpenAI1,455±440,297—
48▼ 1claude-sonnet-4-5-20250929ClosedAnthropic1,455±379,687—
49—gpt-5.6-luna-xhighClosedOpenAI1,452±522,852—
50▲ 1claude-opus-4-1-20250805-thinking-16kClosedAnthropic1,450±348,803—

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 “—”.