Skip to content
IFAI

Model rankings

137 models · 1 boards · 1 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published November 22, 2024

Most preferred
o1-previewOpenAI1,301Score
Best open model
Best from China
yi-lightning01 AI1,245Score
Most voted
claude-3-opus-20240229Anthropic186,718Votes
Top three by Score
1o1-previewOpenAI1,301
3gemini-1.5-pro-002Google1,266
Top three open models
1llama-3.1-405b-instruct-fp8Meta · #7 overall1,252
2llama-3.1-405b-instruct-bf16Meta · #8 overall1,251
3mistral-large-2407Mistral · #18 overall1,230
RankChangeModelScore95% intervalVotesPrice $/M
1—o1-previewClosedOpenAI1,301±427,835—
2—claude-3-5-sonnet-20241022ClosedAnthropic · 1 more variant1,283±429,454—
3—gemini-1.5-pro-002ClosedGoogle1,266±327,336—
4—gpt-4o-2024-05-13ClosedOpenAI1,262±3111,745—
5—o1-miniClosedOpenAI1,258±331,992—
6—gemini-advanced-0514ClosedGoogle1,253±352,221—
7—llama-3.1-405b-instruct-fp8OpenMeta1,252±352,089—
8—llama-3.1-405b-instruct-bf16OpenMeta1,251±414,596—
9▲ 1gpt-4o-2024-08-06ClosedOpenAI1,249±343,776—
10▼ 1grok-2-2024-08-13ClosedxAI1,249±352,102—
11—gpt-4-turbo-2024-04-09ClosedOpenAI1,241±2102,279—
12—gemini-1.5-pro-001ClosedGoogle1,240±382,614—
13—claude-3-opus-20240229ClosedAnthropic1,238±2186,718—
14—gpt-4-1106-previewClosedOpenAI1,234±3103,847—
15—gpt-4o-mini-2024-07-18ClosedOpenAI1,233±351,690—
16—gpt-4-0125-previewClosedOpenAI1,230±397,195—
17—gemini-1.5-flash-002ClosedGoogle1,228±421,071—
18—grok-2-mini-2024-08-13ClosedxAI1,223±442,192—
19—llama-3.1-nemotron-70b-instructOpenNVIDIA1,215±77,270—
20—llama-3.1-70b-instructOpenMeta1,213±347,975—
21—gemma-2-27b-itOpenGoogle1,206±357,595—
22—llama-3.1-nemotron-51b-instructOpenNVIDIA1,204±93,942—
23—gemini-1.5-flash-001ClosedGoogle1,203±365,786—
24—gpt-4-0314ClosedOpenAI1,200±355,965—
25—claude-3-sonnet-20240229ClosedAnthropic1,197±2113,046—
26—nemotron-4-340b-instructOpenNVIDIA1,196±320,637—
27—llama-3-70b-instructOpenMeta1,195±2163,859—
28—gpt-4-0613ClosedOpenAI1,186±391,629—
29—gemma-2-9b-itOpenGoogle1,177±341,124—
30—claude-3-haiku-20240307ClosedAnthropic1,177±2122,399—
31—gemini-1.5-flash-8b-001ClosedGoogle1,176±422,443—
32—gemini-pro-dev-apiClosedGoogle1,147±518,783—
33—llama-3-8b-instructOpenMeta1,142±2109,293—
34—gpt-3.5-turbo-0125ClosedOpenAI · 1 more variant1,137±368,870—
35—gemini-proClosedGoogle1,131±76,558—
36—llama-3.1-8b-instructOpenMeta1,131±346,435—
37—phi-3-medium-4k-instructOpenMicrosoft1,118±426,140—
38—dbrx-instruct-previewOpenDatabricks1,113±433,724—
39—gemma-2-2b-itOpenGoogle1,113±432,637—
40Newgranite-3.0-8b-instructOpenIBM1,110±77,101—
41▼ 1wizardlm-70bOpenMicrosoft1,104±68,380—
42▼ 1snowflake-arctic-instructOpenSnowflake1,102±334,150—
43▼ 1phi-3-small-8k-instructOpenMicrosoft1,098±418,504—
44▼ 1gemma-1.1-7b-itOpenGoogle1,098±425,071—
45▼ 1llama-3.2-3b-instructOpenMeta1,093±78,448—
46Newgranite-3.0-2b-instructOpenIBM1,083±87,284—
47▼ 2llama-2-70b-chatOpenMeta1,081±339,612—
48▼ 2llama2-70b-steerlm-chatOpenNVIDIA1,074±113,636—
49▼ 2phi-3-mini-4k-instruct-june-2024OpenMicrosoft1,068±612,867—
50▼ 2wizardlm-13bOpenMicrosoft1,063±67,183—

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 “—”.