Skip to content
IFAI

Model rankings

127 models · 1 boards · 1 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published October 15, 2024

Most preferred
o1-previewOpenAI1,300Score
Best open model
Best from China
yi-lightning01 AI1,243Score
Most voted
claude-3-opus-20240229Anthropic174,238Votes
Top three by Score
1o1-previewOpenAI1,300
2gemini-1.5-pro-002Google1,271
3gpt-4o-2024-05-13OpenAI1,262
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 · #19 overall1,230
RankChangeModelScore95% intervalVotesPrice $/M
1—o1-previewClosedOpenAI1,300±517,562—
2—gemini-1.5-pro-002ClosedGoogle1,271±611,430—
3—gpt-4o-2024-05-13ClosedOpenAI1,262±299,251—
4—o1-miniClosedOpenAI1,260±517,919—
5—claude-3-5-sonnet-20240620ClosedAnthropic1,259±375,957—
6—gemini-advanced-0514ClosedGoogle1,252±352,235—
7▲ 1llama-3.1-405b-instruct-fp8OpenMeta1,252±339,428—
8▼ 1llama-3.1-405b-instruct-bf16OpenMeta1,251±514,496—
9—grok-2-2024-08-13ClosedxAI1,249±435,661—
10—gpt-4o-2024-08-06ClosedOpenAI1,247±430,976—
11—gpt-4-turbo-2024-04-09ClosedOpenAI1,241±297,256—
12—gemini-1.5-pro-api-0514ClosedGoogle1,239±289,220—
13—claude-3-opus-20240229ClosedAnthropic1,238±2174,238—
14—gpt-4-1106-previewClosedOpenAI1,234±2101,579—
15—gpt-4o-mini-2024-07-18ClosedOpenAI1,232±338,831—
16—gpt-4-0125-previewClosedOpenAI1,230±294,862—
17▲ 1gemini-1.5-flash-002ClosedGoogle1,225±68,957—
18▼ 1grok-2-mini-2024-08-13ClosedxAI1,221±430,597—
19—llama-3.1-70b-instructOpenMeta1,210±334,744—
20—gemma-2-27b-itOpenGoogle1,205±346,053—
21—gemini-1.5-flash-api-0514ClosedGoogle1,202±369,151—
22—gpt-4-0314ClosedOpenAI1,200±455,979—
23—claude-3-sonnet-20240229ClosedAnthropic1,197±2113,073—
24—nemotron-4-340b-instructOpenNVIDIA1,196±420,656—
25—llama-3-70b-instructOpenMeta1,194±2163,997—
26—gpt-4-0613ClosedOpenAI1,186±291,686—
27—claude-3-haiku-20240307ClosedAnthropic1,177±2119,440—
28▲ 1gemini-1.5-flash-8b-001ClosedGoogle1,177±510,389—
29▼ 1gemma-2-9b-itOpenGoogle1,175±334,626—
30—gemini-pro-dev-apiClosedGoogle1,147±418,790—
31—llama-3-8b-instructOpenMeta1,142±2109,414—
32—gpt-3.5-turbo-0125ClosedOpenAI · 1 more variant1,138±368,912—
33—gemini-proClosedGoogle1,130±86,560—
34—llama-3.1-8b-instructOpenMeta1,125±332,937—
35—phi-3-medium-4k-instructOpenMicrosoft1,119±426,163—
36—dbrx-instruct-previewOpenDatabricks1,114±333,735—
37—gemma-2-2b-itOpenGoogle1,110±426,098—
38—wizardlm-70bOpenMicrosoft1,105±68,385—
39—snowflake-arctic-instructOpenSnowflake1,103±334,179—
40▲ 1phi-3-small-8k-instructOpenMicrosoft1,098±418,492—
41▼ 1gemma-1.1-7b-itOpenGoogle1,097±425,097—
42—llama-3.2-3b-instructOpenMeta1,090±78,620—
43—llama-2-70b-chatOpenMeta1,081±339,641—
44—llama2-70b-steerlm-chatOpenNVIDIA1,070±93,638—
45—phi-3-mini-4k-instruct-june-2024OpenMicrosoft1,068±512,886—
46—wizardlm-13bOpenMicrosoft1,064±67,184—
47—phi-3-mini-4k-instructOpenMicrosoft1,055±421,122—
48—llama-2-13b-chatOpenMeta1,053±419,737—
49—phi-3-mini-128k-instructOpenMicrosoft1,048±421,618—
50—gemma-7b-itOpenGoogle1,047±79,182—

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 “—”.