Skip to content
IFAI

Model rankings

167 models · 2 boards · 1 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published January 28, 2025

Most preferred
o1-2024-12-17OpenAI1,322Score
Best open model
deepseek-r1DeepSeek1,316Score
Best from China
deepseek-r1DeepSeek1,316Score
Most voted
claude-3-opus-20240229Anthropic202,735Votes
Top three by Score
1o1-2024-12-17OpenAI1,322
2deepseek-r1DeepSeek1,316
3o1-previewOpenAI1,303
Top three open models
1deepseek-r1DeepSeek · #2 overall1,316
2deepseek-v3DeepSeek · #5 overall1,275
3llama-3.1-405b-instruct-bf16Meta · #10 overall1,254
RankChangeModelScore95% intervalVotesPrice $/M
1—o1-2024-12-17ClosedOpenAI1,322±69,997—
2—o1-previewClosedOpenAI1,303±433,181—
3—claude-3-5-sonnet-20241022ClosedAnthropic · 1 more variant1,286±449,688—
4—gemini-1.5-pro-002ClosedGoogle1,269±347,401—
5—gpt-4o-2024-05-13ClosedOpenAI1,264±2117,744—
6—o1-miniClosedOpenAI1,257±350,741—
7—gemini-advanced-0514ClosedGoogle1,254±352,139—
8—step-2-16k-exp-202412ClosedStepFun1,252±74,774—
9—gpt-4o-2024-08-06ClosedOpenAI1,250±347,979—
10—grok-2-2024-08-13ClosedxAI1,249±367,139—
11—yi-lightningClosed01 AI1,247±428,948—
12—gpt-4-turbo-2024-04-09ClosedOpenAI1,242±2102,139—
13—gemini-1.5-pro-001ClosedGoogle1,241±382,432—
14—claude-3-opus-20240229ClosedAnthropic1,239±2202,735—
15▲ 2glm-4-plusClosedZhipu AI1,235±427,769—
16—gpt-4o-mini-2024-07-18ClosedOpenAI1,235±361,628—
17▲ 1gpt-4-1106-previewClosedOpenAI1,235±2103,727—
18▼ 3claude-3-5-haiku-20241022ClosedAnthropic1,234±512,959—
19—qwen2.5-plus-1127ClosedAlibaba1,232±59,841—
20—gpt-4-0125-previewClosedOpenAI1,231±397,064—
21—gemini-1.5-flash-002ClosedGoogle1,230±335,593—
22—grok-2-mini-2024-08-13ClosedxAI1,225±355,500—
23—reka-core-20240904ClosedReka AI1,208±77,942—
24—amazon-nova-pro-v1.0ClosedAmazon1,208±514,117—
25—gemini-1.5-flash-001ClosedGoogle1,205±365,651—
26—gpt-4-0314ClosedOpenAI1,200±355,953—
27—claude-3-sonnet-20240229ClosedAnthropic1,197±2113,016—
28—reka-flash-20240904ClosedReka AI1,193±68,131—
29—glm-4-0520ClosedZhipu AI1,189±510,214—
30—gpt-4-0613ClosedOpenAI1,185±291,647—
31—amazon-nova-lite-v1.0ClosedAmazon1,184±511,952—
32—gemini-1.5-flash-8b-001ClosedGoogle1,180±437,250—
33—claude-3-haiku-20240307ClosedAnthropic1,178±3122,300—
34—amazon-nova-micro-v1.0ClosedAmazon1,163±612,039—
35—mistral-large-2402ClosedMistral1,158±364,927—
36—hunyuan-standard-256kClosedTencent1,153±102,901—
37—reka-flash-21b-20240226-onlineClosedReka AI1,151±516,029—
38—gemini-pro-dev-apiClosedGoogle1,147±418,793—
39—reka-flash-21b-20240226ClosedReka AI1,142±425,799—
40—mistral-mediumClosedMistral1,141±435,554—
41—gpt-3.5-turbo-0125ClosedOpenAI · 1 more variant1,137±368,861—
42—gemini-proClosedGoogle1,132±76,558—
43—palm-2ClosedGoogle1,042±88,741—

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 “—”.