Skip to content
IFAI

Model rankings

130 models · 1 boards · 1 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published October 28, 2024

Most preferred
o1-previewOpenAI1,302Score
Best open model
Best from China
yi-lightning01 AI1,241Score
Most voted
claude-3-opus-20240229Anthropic177,919Votes
Top three by Score
1o1-previewOpenAI1,302
3gemini-1.5-pro-002Google1,269
Top three open models
1llama-3.1-405b-instruct-fp8Meta · #7 overall1,251
2llama-3.1-405b-instruct-bf16Meta · #8 overall1,251
3mistral-large-2407Mistral · #19 overall1,229
RankChangeModelScore95% intervalVotesPrice $/M
1—o1-previewClosedOpenAI1,302±521,071—
2▲ 2claude-3-5-sonnet-20241022ClosedAnthropic · 1 more variant1,287±77,284—
3▼ 1gemini-1.5-pro-002ClosedGoogle1,269±515,736—
4▼ 1gpt-4o-2024-05-13ClosedOpenAI1,262±3102,960—
5—o1-miniClosedOpenAI1,256±423,128—
6—gemini-advanced-0514ClosedGoogle1,253±352,235—
7—llama-3.1-405b-instruct-fp8OpenMeta1,251±343,099—
8—llama-3.1-405b-instruct-bf16OpenMeta1,251±514,607—
9—grok-2-2024-08-13ClosedxAI1,248±440,873—
10—gpt-4o-2024-08-06ClosedOpenAI1,248±334,765—
11—gpt-4-turbo-2024-04-09ClosedOpenAI1,241±399,055—
12—gemini-1.5-pro-001ClosedGoogle1,239±382,665—
13—claude-3-opus-20240229ClosedAnthropic1,238±2177,919—
14—gpt-4-1106-previewClosedOpenAI1,234±3103,422—
15—gpt-4o-mini-2024-07-18ClosedOpenAI1,231±342,661—
16—gpt-4-0125-previewClosedOpenAI1,230±296,746—
17—gemini-1.5-flash-002ClosedGoogle1,227±512,379—
18—grok-2-mini-2024-08-13ClosedxAI1,222±434,105—
19▲ 1llama-3.1-nemotron-70b-instructOpenNVIDIA1,215±96,228—
20Newllama-3.1-nemotron-51b-instructOpenNVIDIA1,212±131,816—
21▼ 2llama-3.1-70b-instructOpenMeta1,211±338,692—
22▼ 1gemma-2-27b-itOpenGoogle1,205±349,844—
23▼ 1gemini-1.5-flash-001ClosedGoogle1,202±365,822—
24▼ 1gpt-4-0314ClosedOpenAI1,200±355,981—
25▼ 1claude-3-sonnet-20240229ClosedAnthropic1,197±2113,087—
26▼ 1nemotron-4-340b-instructOpenNVIDIA1,196±520,649—
27▼ 1llama-3-70b-instructOpenMeta1,194±2163,932—
28▼ 1gpt-4-0613ClosedOpenAI1,186±291,680—
29▼ 1claude-3-haiku-20240307ClosedAnthropic1,177±2121,352—
30—gemini-1.5-flash-8b-001ClosedGoogle1,176±513,402—
31▼ 2gemma-2-9b-itOpenGoogle1,176±336,551—
32▼ 1gemini-pro-dev-apiClosedGoogle1,147±518,789—
33▼ 1llama-3-8b-instructOpenMeta1,142±3109,378—
34▼ 1gpt-3.5-turbo-0125ClosedOpenAI · 1 more variant1,137±368,902—
35▼ 1gemini-proClosedGoogle1,131±86,561—
36▼ 1llama-3.1-8b-instructOpenMeta1,127±336,916—
37▼ 1phi-3-medium-4k-instructOpenMicrosoft1,118±426,158—
38▼ 1dbrx-instruct-previewOpenDatabricks1,113±333,730—
39▼ 1gemma-2-2b-itOpenGoogle1,110±428,101—
40▼ 1wizardlm-70bOpenMicrosoft1,104±78,384—
41▼ 1snowflake-arctic-instructOpenSnowflake1,103±334,178—
42▼ 1phi-3-small-8k-instructOpenMicrosoft1,098±518,500—
43▼ 1gemma-1.1-7b-itOpenGoogle1,098±425,082—
44▼ 1llama-3.2-3b-instructOpenMeta1,093±78,459—
45▼ 1llama-2-70b-chatOpenMeta1,081±439,630—
46▼ 1llama2-70b-steerlm-chatOpenNVIDIA1,074±103,640—
47▼ 1phi-3-mini-4k-instruct-june-2024OpenMicrosoft1,068±612,882—
48▼ 1wizardlm-13bOpenMicrosoft1,063±87,183—
49▼ 1phi-3-mini-4k-instructOpenMicrosoft1,055±421,126—
50▼ 1llama-2-13b-chatOpenMeta1,053±519,725—

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 “—”.