Skip to content
IFAI

Model rankings

1412 models · 5 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published August 12, 2026

Most preferred
claude-fable-5Anthropic1,507Score
Best open model
kimi-k3-maxMoonshot AI1,489Score
Best from China
qwen3.8-maxAlibaba1,491Score
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 · #11 overall1,489
2glm-5.2-maxZ.ai · #32 overall1,471
3mimo-v2.5-proXiaomi · #37 overall1,468
This week's changes
Qwen-Audio-3.0-TTS-PlusSpeech · #2New
Qwen3.8 MaxIntelligence · #5New
grok-4.6-highCoding · #5New
Muse Spark 1.2 (xhigh)Intelligence · #7New
gemini-3.7-flash-highCoding · #8New
RankChangeModelScore95% intervalVotesPrice $/M
1—claude-fable-5ClosedAnthropic1,507±521,439—
2Newclaude-opus-4-6-highClosedAnthropic1,505±472,466—
3Newclaude-opus-4-7-highClosedAnthropic1,502±460,268—
4—muse-spark-1.2 (xHigh)ClosedMeta1,499±103,259—
5—claude-opus-4-6ClosedAnthropic1,497±376,428—
6▲ 1claude-opus-4-7ClosedAnthropic1,494±461,369—
7▲ 1claude-opus-5-highClosedAnthropic1,494±519,792—
8▲ 1claude-opus-5-maxClosedAnthropic1,491±79,559—
9▼ 3qwen3.8-maxClosedAlibaba1,491±86,908$3.0
10▲ 1muse-spark-1.1ClosedMeta1,489±616,805—
11▲ 3kimi-k3-maxOpenMoonshot AI1,489±611,864—
12▼ 2muse-sparkClosedMeta1,488±613,596—
13▼ 1gemini-3.1-pro-previewClosedGoogle1,486±394,989—
14▼ 1gemini-3-proClosedGoogle1,485±441,505—
15Newgemini-3.6-flash-highClosedGoogle1,484±613,693—
16Newclaude-opus-4-8-highClosedAnthropic1,482±540,588—
17—gpt-5.5-highClosedOpenAI1,482±455,322—
18—gpt-5.6-sol-xhighClosedOpenAI1,481±615,450—
19▲ 2gemini-3.5-flash-highClosedGoogle1,477±525,746—
20—gpt-5.5ClosedOpenAI1,477±456,647—
21▼ 2gpt-5.4-highClosedOpenAI1,477±460,819—
22—gpt-5.2-chat-latest-20260210ClosedOpenAI1,476±434,380—
23▲ 2gemini-3.5-flash-mediumClosedGoogle1,475±523,928—
24—grok-4.20-beta1ClosedxAI1,475±526,813—
25▼ 2qwen3.7-max-previewClosedAlibaba1,474±103,718—
26▲ 2claude-opus-4-8ClosedAnthropic1,474±541,219—
27▼ 1gpt-5.5-instantClosedOpenAI1,473±525,900—
28▼ 1gemini-3-flashClosedGoogle1,473±430,859—
29Newclaude-opus-4-5-20251101-high-32kClosedAnthropic1,473±437,217—
30—claude-sonnet-4-6ClosedAnthropic1,472±466,602—
31—grok-4.20-beta-0309-reasoningClosedxAI1,472±462,379—
32▲ 1glm-5.2-maxOpenZ.ai1,471±526,867—
33▼ 1grok-4.20-multi-agent-beta-0309ClosedxAI1,471±460,964—
34—claude-opus-4-5-20251101ClosedAnthropic1,469±371,044—
35—grok-4.5ClosedxAI1,468±517,738—
36▲ 1ernie-5.1ClosedBaidu1,468±537,213—
37▲ 2mimo-v2.5-proOpenXiaomi1,468±450,613—
38▼ 2glm-5.1OpenZ.ai1,467±439,063—
39▲ 2qwen3.5-max-previewClosedAlibaba1,466±521,506—
40—grok-4.1-thinkingClosedxAI1,465±365,600—
41▲ 1gpt-5.4ClosedOpenAI1,465±463,759—
42▼ 4gpt-5.6-terra-xhighClosedOpenAI1,465±616,008—
43Newgrok-4.6-highClosedxAI1,464±122,448—
44▼ 1claude-sonnet-5-highClosedAnthropic1,462±523,138—
45▼ 1kimi-k2.6OpenMoonshot AI1,461±537,619—
46▼ 1qwen3.6-max-previewClosedAlibaba1,460±85,206—
47▼ 1grok-4.1ClosedxAI1,459±367,816—
48▲ 1qwen3.7-plusClosedAlibaba1,458±530,730—
49▼ 1gemini-3-flash (thinking-minimal)ClosedGoogle1,458±386,485—
50—deepseek-v4-proOpenDeepSeek1,458±454,288—

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 “—”.