Skip to content
IFAI

Model rankings

1539 models · 5 boards · 2 sources

‹
Week of September 28, 2026
November 9, 202636 changesNovember 2, 202641 changesOctober 26, 20269 changesOctober 19, 2026247 changesOctober 12, 2026127 changesOctober 5, 202634 changesSeptember 28, 202617 changesSeptember 21, 2026115 changesSeptember 14, 2026174 changesSeptember 7, 2026144 changesAugust 31, 202620 changesAugust 24, 202615 changes
›
Artificial AnalysisIntelligence IndexArenaText arena

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

Most preferred
gemini-4-argon-highGoogle1,525Score
Best open model
kimi-k3-maxMoonshot AI1,488Score
Best from China
kimi-k3-maxMoonshot AI1,488Score
Most voted
claude-3-opus-20240229Anthropic194,909Votes
Top three by Score
1gemini-4-argon-highGoogle1,525
2claude-opus-4-6-highAnthropic1,505
3claude-fable-5-highAnthropic1,504
Top three open models
1kimi-k3-maxMoonshot AI · #16 overall1,488
2mimo-v2.6-proXiaomi · #26 overall1,480
3glm-5.3-maxZ.ai · #27 overall1,478
This week's changes
Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)Intelligence · #1New
Eleven v4Speech · #1New
Qwen-Audio-3.1-TTS-PlusSpeech · #2New
claude-sonnet-5.5-xhighCoding · #3New
gpt-6.1-sol-maxCoding · #4New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortScoreLowest price
RankChangeModelScore95% intervalVotesPrice $/M
1Newgemini-4-argon-highClosedGoogle1,525±94,932—
2—claude-opus-4-6-highClosedAnthropic1,505±377,636—
3—claude-fable-5-highClosedAnthropic1,504±438,387—
4▼ 3claude-opus-5.5-highClosedAnthropic1,504±94,552—
5▼ 1claude-opus-4-7-highClosedAnthropic1,501±464,946—
6▼ 1claude-fable-5.1-maxClosedAnthropic1,501±611,800—
7▼ 1claude-opus-4-6ClosedAnthropic1,497±382,189—
8▲ 2gemini-3.8-flash-highClosedGoogle1,495±526,298—
9—muse-spark-1.3-maxClosedMeta1,494±612,343—
10▼ 2claude-opus-4-7ClosedAnthropic1,494±466,058—
11▼ 4muse-spark-1.2 (xHigh)ClosedMeta1,494±94,356—
12—muse-spark-1.1ClosedMeta1,491±437,238—
13▼ 2claude-opus-5-highClosedAnthropic1,490±459,482—
14—claude-opus-5-maxClosedAnthropic1,489±528,937—
15▼ 2muse-sparkClosedMeta1,489±614,120—
16—kimi-k3-maxOpenMoonshot AI1,488±528,280—
17▼ 2gemini-3.7-flash-highClosedGoogle1,488±521,539—
18▼ 1gemini-3.1-pro-previewClosedGoogle1,487±3121,806—
19▼ 1gemini-3-proClosedGoogle1,485±441,910—
20▼ 1gpt-5.6-sol-xhighClosedOpenAI1,484±436,656—
21Newgpt-6.1-sol-maxClosedOpenAI1,483±113,071—
22▼ 2gemini-3.6-flash-highClosedGoogle1,483±436,070—
23▲ 2qwen3.8-maxClosedAlibaba1,482±523,353$3.0
24▼ 2claude-opus-4-8-highClosedAnthropic1,482±463,974—
25▼ 4gpt-5.5-highClosedOpenAI1,481±469,202—
26▼ 3mimo-v2.6-proOpenXiaomi1,480±94,056$0.54
27▼ 3glm-5.3-maxOpenZ.ai1,478±617,857—
28▼ 1gemini-3.5-flash-highClosedGoogle1,477±448,420—
29▼ 3gpt-6-astra-maxClosedOpenAI1,477±79,156—
30▼ 2gpt-5.5ClosedOpenAI1,477±470,781—
31▲ 5gemini-3.5-flash-mediumClosedGoogle1,476±447,187—
32▼ 1glm-5.2-maxOpenZ.ai1,476±445,399—
33▼ 3gpt-5.2-chat-latest-20260210ClosedOpenAI1,476±435,937—
34▼ 2gpt-5.4-highClosedOpenAI1,475±464,642—
35▼ 2qwen3.7-max-previewClosedAlibaba1,475±103,920—
36▼ 2grok-4.20-beta1ClosedxAI1,475±527,827—
37—claude-opus-4-8ClosedAnthropic1,475±465,072—
38▼ 9deepseek-v4.1-flash-maxOpenDeepSeek1,474±78,728—
39▼ 1claude-opus-4-5-20251101-high-32kClosedAnthropic1,474±437,448—
40▼ 1gpt-5.5-instantClosedOpenAI1,473±527,098—
41▼ 6glm-5.3-flashOpenZ.ai1,473±522,971$0.24
42▼ 2gemini-3-flashClosedGoogle · 1 more variant1,473±431,259—
43▼ 2claude-sonnet-4-6ClosedAnthropic1,472±470,747—
44▼ 2grok-4.20-beta-0309-reasoningClosedxAI1,472±466,334—
45Newclaude-sonnet-5.5-xhighClosedAnthropic1,471±103,145—
46▼ 3grok-4.20-multi-agent-beta-0309ClosedxAI1,471±464,788—
47▼ 3claude-opus-4-5-20251101ClosedAnthropic1,470±372,772—
48▼ 3ernie-5.1ClosedBaidu1,468±539,396—
49▼ 3mimo-v2.5-proOpenXiaomi1,468±470,871—
50▼ 3grok-4.5ClosedxAI1,466±439,789—

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 “—”.