Skip to content
IFAI

Model rankings

1542 models · 5 boards · 2 sources

‹
Week of October 12, 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 15, 2026

Most preferred
Gemini 4 Argon (High)Google1,524Score
Best open model
Kimi K3 (Max)Moonshot AI1,487Score
Best from China
Kimi K3 (Max)Moonshot AI1,487Score
Most voted
claude-3-opus-20240229Anthropic194,909Votes
Top three by Score
1Gemini 4 Argon (High)Google1,524
2Muse Wonder (Max)Meta1,509
3Claude Opus 5.5 (High)Anthropic1,508
Top three open models
1Kimi K3 (Max)Moonshot AI · #15 overall1,487
2mimo-v2.6-proXiaomi · #24 overall1,479
3glm-5.3-maxZ.ai · #25 overall1,479
This week's changes
Claude Opus 5.5 (Max)Coding · #1New
Eleven v4 TurboSpeech · #1New
GPT-6 Astra (Max)Coding · #2New
Claude Sonnet 5.5 (xHigh)Coding · #3New
GPT-6.1 Sol (Max)Coding · #4New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortScoreLowest price
RankChangeModelScore95% intervalVotesPrice $/M
1NewGemini 4 Argon (High)ClosedGoogle1,524±94,904$8.0
2NewMuse Wonder (Max)ClosedMeta1,509±113,247$8.0
3NewClaude Opus 5.5 (High)ClosedAnthropic1,508±78,300$8.0
4NewClaude Fable 5 (High)ClosedAnthropic1,504±442,004—
5▲ 2Claude Opus 4.6 (High)ClosedAnthropic · 1 more variant1,503±381,394—
6NewClaude Fable 5.1 (Max)ClosedAnthropic1,502±614,590$20
7▲ 3Claude Opus 4.7 (High)ClosedAnthropic · 1 more variant1,501±465,116—
8NewGemini 3.8 Flash (High)ClosedGoogle1,496±537,454$1.5
9NewMuse Spark 1.3 (Max)ClosedMeta1,494±617,561$2.0
10▲ 1Muse Spark 1.2 (xHigh)ClosedMeta1,493±78,248—
11▲ 1Muse Spark 1.1ClosedMeta1,490±442,810—
12NewClaude Opus 5 (Max)ClosedAnthropic · 1 more variant1,490±532,495$10
13▲ 2Muse SparkClosedMeta1,489±614,150—
14NewGemini 3.7 Flash (High)ClosedGoogle1,488±527,232—
15NewGemini 3.1 Pro PreviewClosedGoogle1,487±3127,649—
16▲ 2Gemini 3 ProClosedGoogle1,485±442,072—
17▲ 2gpt-5.6-sol-xhighClosedOpenAI1,485±440,442—
18▲ 2gpt-6.1-sol-maxClosedOpenAI1,484±86,320—
19▲ 3gemini-3.6-flash-highClosedGoogle1,483±436,122—
20▲ 1qwen3.8-maxClosedAlibaba1,482±527,766$3.0
21▲ 3claude-opus-4-8-highClosedAnthropic1,481±464,100—
22▲ 1gpt-5.5-highClosedOpenAI1,481±469,401—
23▲ 2gemini-3.5-flash-highClosedGoogle1,477±448,486—
24▲ 7gpt-6-astra-maxClosedOpenAI1,477±612,163—
25▲ 1gpt-5.5ClosedOpenAI1,477±470,985—
26▲ 1gemini-3.5-flash-mediumClosedGoogle1,476±447,292—
27▲ 1gpt-5.2-chat-latest-20260210ClosedOpenAI1,476±435,999—
28▲ 2gpt-5.4-highClosedOpenAI1,475±464,776—
29—claude-sonnet-5.5-xhighClosedAnthropic1,475±86,831—
30▲ 3grok-4.20-beta1ClosedxAI1,475±527,908—
31▲ 1qwen3.7-max-previewClosedAlibaba1,474±103,934—
32▲ 2claude-opus-4-8ClosedAnthropic1,474±465,172—
33▲ 2claude-opus-4-5-20251101-high-32kClosedAnthropic1,474±437,509—
34▲ 2gpt-5.5-instantClosedOpenAI1,473±527,158—
35▲ 2gemini-3-flashClosedGoogle · 1 more variant1,473±431,325—
36▲ 2claude-sonnet-4-6ClosedAnthropic1,472±470,931—
37▲ 2grok-4.20-beta-0309-reasoningClosedxAI1,472±466,436—
38▲ 2grok-4.20-multi-agent-beta-0309ClosedxAI1,470±464,946—
39▲ 2claude-opus-4-5-20251101ClosedAnthropic1,470±372,899—
40▲ 2ernie-5.1ClosedBaidu1,467±539,468—
41▲ 2gpt-5.6-terra-xhighClosedOpenAI1,466±443,271—
42▲ 2grok-4.5ClosedxAI1,466±439,896—
43▲ 2grok-4.1-thinkingClosedxAI · 1 more variant1,465±366,509—
44▲ 2gpt-5.4ClosedOpenAI1,465±467,870—
45▲ 2qwen3.5-max-previewClosedAlibaba1,464±522,600—
46▲ 2claude-sonnet-5-highClosedAnthropic1,461±449,595—
47▲ 2qwen3.6-max-previewClosedAlibaba1,461±85,426—
48▲ 5gpt-6-sol-maxClosedOpenAI1,459±612,466—
49▲ 1claude-sonnet-4-5-20250929-high-32kClosedAnthropic1,456±383,940—
50▲ 1dola-seed-2.0-proClosedByteDance1,456±379,140—

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 “—”.