Skip to content
IFAI

Model rankings

1501 models · 5 boards · 2 sources

‹
Week of September 14, 2026
October 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 changesAugust 17, 202633 changesAugust 10, 2026116 changes
›
Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published September 13, 2026

Most preferred
claude-fable-5Anthropic1,506Score
Best open model
kimi-k3-maxMoonshot AI1,485Score
Best from China
kimi-k3-maxMoonshot AI1,485Score
Most voted
claude-3-opus-20240229Anthropic194,909Votes
Top three by Score
1claude-fable-5Anthropic1,506
2claude-opus-4-6-highAnthropic1,505
3claude-opus-4-7-highAnthropic1,502
Top three open models
1kimi-k3-maxMoonshot AI · #17 overall1,485
2glm-5.3-maxZ.ai · #19 overall1,483
3glm-5.3-flashZ.ai · #29 overall1,475
This week's changes
GPT Image 2.5 Flare (max)Image · #1New
GPT Image 2.5 Sunburst (max)Image · #2New
DeepSeek V4.1 Flash (Reasoning, Max Effort)Intelligence · #20New
Agnes 3.0 FlashIntelligence · #27New
Ling-3.0-flash-VLIntelligence · #77New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortScoreLowest price
RankChangeModelScore95% intervalVotesPrice $/M
1—claude-fable-5ClosedAnthropic1,506±530,057—
2—claude-opus-4-6-highClosedAnthropic1,505±471,993—
3—claude-opus-4-7-highClosedAnthropic1,502±460,002—
4—muse-spark-1.2 (xHigh)ClosedMeta1,500±113,227—
5—claude-fable-5.1-maxClosedAnthropic1,498±85,783—
6—claude-opus-4-6ClosedAnthropic1,497±375,878—
7—claude-opus-4-7ClosedAnthropic1,494±461,128—
8—muse-spark-1.3-maxClosedMeta1,493±94,723—
9—gemini-3.8-flash-highClosedGoogle1,493±95,076—
10—claude-opus-5-highClosedAnthropic1,493±442,617—
11—muse-spark-1.1ClosedMeta1,493±527,615—
12—gemini-3.7-flash-highClosedGoogle1,490±85,640—
13—muse-sparkClosedMeta1,488±613,565—
14—claude-opus-5-maxClosedAnthropic1,487±520,706—
15—gemini-3.1-pro-previewClosedGoogle1,487±3106,951—
16—gemini-3-proClosedGoogle1,485±440,654—
17—gpt-5.6-sol-xhighClosedOpenAI1,483±527,069—
18—gpt-5.5-highClosedOpenAI1,482±464,924—
19—claude-opus-4-8-highClosedAnthropic1,481±452,535—
20—qwen3.8-maxClosedAlibaba1,481±616,670$3.0
21—gemini-3.6-flash-highClosedGoogle1,480±526,445—
22—gpt-6-astra-maxClosedOpenAI1,480±122,693—
23—gemini-3.5-flash-highClosedGoogle1,478±438,257—
24—gpt-5.4-highClosedOpenAI1,476±460,537—
25—gpt-5.2-chat-latest-20260210ClosedOpenAI1,476±434,176—
26—gpt-5.5ClosedOpenAI1,476±466,317—
27—grok-4.20-beta1ClosedxAI1,475±526,599—
28—gemini-3.5-flash-mediumClosedGoogle1,474±436,627—
29—gpt-5.5-instantClosedOpenAI1,474±525,850—
30—gemini-3-flashClosedGoogle · 1 more variant1,474±430,225—
31—qwen3.7-max-previewClosedAlibaba1,473±103,705—
32—claude-opus-4-8ClosedAnthropic1,473±453,446—
33—claude-opus-4-5-20251101-high-32kClosedAnthropic1,473±436,239—
34—claude-sonnet-4-6ClosedAnthropic1,473±466,208—
35—grok-4.20-beta-0309-reasoningClosedxAI1,471±462,168—
36—grok-4.20-multi-agent-beta-0309ClosedxAI1,470±460,777—
37—claude-opus-4-5-20251101ClosedAnthropic1,469±370,013—
38—grok-4.5ClosedxAI1,468±530,103—
39—ernie-5.1ClosedBaidu1,468±537,058—
40—gpt-5.6-terra-xhighClosedOpenAI1,466±528,119—
41—gpt-5.4ClosedOpenAI1,466±463,526—
42—grok-4.1-thinkingClosedxAI · 1 more variant1,465±364,152—
43—qwen3.5-max-previewClosedAlibaba1,465±521,476—
44—claude-sonnet-5-highClosedAnthropic1,461±535,301—
45—qwen3.6-max-previewClosedAlibaba1,460±85,186—
46—claude-sonnet-4-5-20250929-high-32kClosedAnthropic1,456±380,980—
47—gemini-3.5-flash-liteClosedGoogle1,456±526,165$0.85
48—dola-seed-2.0-proClosedByteDance1,456±374,159—
49—qwen3.7-plusClosedAlibaba1,456±439,334—
50—grok-4.6-highClosedxAI1,456±615,521—

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 “—”.