Skip to content
IFAI

Model rankings

161 models · 2 boards · 1 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published January 5, 2025

Most preferred
o1-2024-12-17OpenAI1,323Score
Best open model
deepseek-v3DeepSeek1,278Score
Best from China
deepseek-v3DeepSeek1,278Score
Most voted
claude-3-opus-20240229Anthropic201,772Votes
Top three by Score
1o1-2024-12-17OpenAI1,323
2o1-previewOpenAI1,303
Top three open models
1deepseek-v3DeepSeek · #4 overall1,278
2llama-3.1-405b-instruct-fp8Meta · #9 overall1,253
3llama-3.1-405b-instruct-bf16Meta · #10 overall1,253
RankChangeModelScore95% intervalVotesPrice $/M
1Newdeepseek-v3OpenDeepSeek1,278±76,639—
2▼ 1yi-lightningClosed01 AI1,247±428,964—
3▼ 1deepseek-v2.5-1210OpenDeepSeek · 1 more variant1,240±77,271—
4▼ 1glm-4-plusClosedZhipu AI1,235±427,768—
5—qwen2.5-plus-1127ClosedAlibaba1,232±74,700—
6▼ 2qwen-max-0919OpenAlibaba1,231±517,436—
7▼ 1qwen2.5-72b-instructOpenAlibaba1,223±338,466—
8▼ 1qwen2.5-coder-32b-instructOpenAlibaba1,190±75,725—
9▼ 1glm-4-0520ClosedZhipu AI1,188±510,217—
10▼ 1deepseek-coder-v2OpenDeepSeek1,182±415,752—
11▼ 1qwen2-72b-instructOpenAlibaba1,181±338,884—
12▼ 1qwen1.5-110b-chatOpenAlibaba1,156±427,470—
13▼ 1hunyuan-standard-256kClosedTencent1,153±92,900—
14▼ 1qwen1.5-72b-chatOpenAlibaba1,148±340,634—
15▼ 1yi-1.5-34b-chatOpen01 AI1,133±325,129—
16▼ 1qwen1.5-32b-chatOpenAlibaba1,127±422,769—
17▼ 1qwen1.5-14b-chatOpenAlibaba1,107±418,679—
18▼ 1yi-34b-chatOpen01 AI1,101±415,928—
19▼ 1deepseek-llm-67b-chatOpenDeepSeek1,091±84,986—
20▼ 1qwq-32b-previewOpenAlibaba1,089±93,420—
21▼ 1qwen1.5-7b-chatOpenAlibaba1,065±84,869—
22▼ 1qwen-14b-chatOpenAlibaba1,057±85,070—
23▼ 1qwen1.5-4b-chatOpenAlibaba1,015±77,811—

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 “—”.