Skip to content
IFAI

Model rankings

165 models · 2 boards · 1 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published January 19, 2025

Most preferred
o1-2024-12-17OpenAI1,323Score
Best open model
deepseek-v3DeepSeek1,279Score
Best from China
deepseek-v3DeepSeek1,279Score
Most voted
claude-3-opus-20240229Anthropic202,735Votes
Top three by Score
1o1-2024-12-17OpenAI1,323
2o1-previewOpenAI1,303
Top three open models
1deepseek-v3DeepSeek · #4 overall1,279
2llama-3.1-405b-instruct-bf16Meta · #9 overall1,254
3llama-3.1-405b-instruct-fp8Meta · #11 overall1,253
RankChangeModelScore95% intervalVotesPrice $/M
1—o1-2024-12-17ClosedOpenAI1,323±77,957—
2—o1-previewClosedOpenAI1,303±433,197—
3—claude-3-5-sonnet-20241022ClosedAnthropic · 1 more variant1,286±447,437—
4—gemini-1.5-pro-002ClosedGoogle1,269±445,203—
5—gpt-4o-2024-05-13ClosedOpenAI1,263±3117,760—
6—o1-miniClosedOpenAI1,257±348,654—
7—gemini-advanced-0514ClosedGoogle1,254±352,148—
8▲ 1llama-3.1-405b-instruct-bf16OpenMeta1,254±521,285—
9▼ 1llama-3.1-405b-instruct-fp8OpenMeta1,253±363,202—
10—gpt-4o-2024-08-06ClosedOpenAI1,250±347,981—
11—grok-2-2024-08-13ClosedxAI1,249±366,281—
12—gpt-4-turbo-2024-04-09ClosedOpenAI1,242±3102,126—
13—gemini-1.5-pro-001ClosedGoogle1,241±382,432—
14—claude-3-opus-20240229ClosedAnthropic1,239±2202,735—
15▲ 1llama-3.3-70b-instructOpenMeta1,235±415,516—
16▼ 1gpt-4o-mini-2024-07-18ClosedOpenAI1,235±460,551—
17—gpt-4-1106-previewClosedOpenAI1,235±3103,732—
18—claude-3-5-haiku-20241022ClosedAnthropic1,234±610,773—
19—gpt-4-0125-previewClosedOpenAI1,231±397,070—
20—gemini-1.5-flash-002ClosedGoogle1,229±434,540—
21—grok-2-mini-2024-08-13ClosedxAI1,225±354,893—
22—llama-3.1-nemotron-70b-instructOpenNVIDIA1,217±67,596—
23—llama-3.1-70b-instructOpenMeta1,214±358,786—
24—llama-3.1-tulu-3-70bOpenAi21,210±103,026—
25—amazon-nova-pro-v1.0ClosedAmazon1,208±513,076—
26—gemma-2-27b-itOpenGoogle1,208±372,425—
27—gemini-1.5-flash-001ClosedGoogle1,205±365,650—
28—llama-3.1-nemotron-51b-instructOpenNVIDIA1,204±93,897—
29—gpt-4-0314ClosedOpenAI1,200±355,965—
30—claude-3-sonnet-20240229ClosedAnthropic1,197±2113,033—
31—nemotron-4-340b-instructOpenNVIDIA1,196±420,609—
32—llama-3-70b-instructOpenMeta1,195±3163,797—
33—gpt-4-0613ClosedOpenAI1,185±391,642—
34—amazon-nova-lite-v1.0ClosedAmazon1,183±510,868—
35Newphi-4OpenMicrosoft1,182±92,485—
36—gemini-1.5-flash-8b-001ClosedGoogle1,180±436,162—
37▼ 2gemma-2-9b-itOpenGoogle1,179±350,239—
38▼ 1claude-3-haiku-20240307ClosedAnthropic1,178±3122,291—
39▼ 1amazon-nova-micro-v1.0ClosedAmazon1,163±510,956—
40—gemini-pro-dev-apiClosedGoogle1,147±418,793—
41▼ 2llama-3.1-tulu-3-8bOpenAi21,147±103,077—
42▼ 1llama-3-8b-instructOpenMeta1,143±3109,211—
43▼ 1gpt-3.5-turbo-0125ClosedOpenAI · 1 more variant1,137±368,873—
44▼ 1llama-3.1-8b-instructOpenMeta1,133±352,646—
45▼ 1gemini-proClosedGoogle1,131±86,559—
46Newgranite-3.1-8b-instructOpenIBM1,131±112,468—
47▼ 2phi-3-medium-4k-instructOpenMicrosoft1,118±426,112—
48▼ 2gemma-2-2b-itOpenGoogle1,116±341,868—
49▼ 2dbrx-instruct-previewOpenDatabricks1,113±333,737—
50▼ 2granite-3.0-8b-instructOpenIBM1,109±77,005—

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 “—”.