Skip to content
IFAI

Model rankings

132 models · 1 boards · 1 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published November 4, 2024

Most preferred
o1-previewOpenAI1,300Score
Best open model
Best from China
yi-lightning01 AI1,243Score
Most voted
claude-3-opus-20240229Anthropic180,601Votes
Top three by Score
1o1-previewOpenAI1,300
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 · #19 overall1,230
RankChangeModelScore95% intervalVotesPrice $/M
1—o1-previewClosedOpenAI1,300±423,562—
2—claude-3-5-sonnet-20241022ClosedAnthropic · 1 more variant1,284±519,005—
3—gemini-1.5-pro-002ClosedGoogle1,266±419,523—
4—gpt-4o-2024-05-13ClosedOpenAI1,262±3105,541—
5—o1-miniClosedOpenAI1,256±526,062—
6—gemini-advanced-0514ClosedGoogle1,253±452,230—
7—llama-3.1-405b-instruct-fp8OpenMeta1,252±345,768—
8—llama-3.1-405b-instruct-bf16OpenMeta1,251±514,608—
9—grok-2-2024-08-13ClosedxAI1,248±343,774—
10—gpt-4o-2024-08-06ClosedOpenAI1,248±437,444—
11—gpt-4-turbo-2024-04-09ClosedOpenAI1,241±2100,404—
12—gemini-1.5-pro-001ClosedGoogle1,239±382,660—
13—claude-3-opus-20240229ClosedAnthropic1,238±2180,601—
14—gpt-4-1106-previewClosedOpenAI1,234±2103,894—
15—gpt-4o-mini-2024-07-18ClosedOpenAI1,231±445,274—
16—gpt-4-0125-previewClosedOpenAI1,230±397,214—
17—gemini-1.5-flash-002ClosedGoogle1,228±515,030—
18—grok-2-mini-2024-08-13ClosedxAI1,222±436,342—
19—llama-3.1-nemotron-70b-instructOpenNVIDIA1,215±66,572—
20▲ 1llama-3.1-70b-instructOpenMeta1,211±341,484—
21▲ 1gemma-2-27b-itOpenGoogle1,205±352,532—
22▲ 1gemini-1.5-flash-001ClosedGoogle1,202±365,808—
23▼ 3llama-3.1-nemotron-51b-instructOpenNVIDIA1,201±93,153—
24—gpt-4-0314ClosedOpenAI1,200±355,978—
25—claude-3-sonnet-20240229ClosedAnthropic1,197±3113,076—
26—nemotron-4-340b-instructOpenNVIDIA1,196±420,645—
27—llama-3-70b-instructOpenMeta1,194±3163,936—
28—gpt-4-0613ClosedOpenAI1,186±391,664—
29—claude-3-haiku-20240307ClosedAnthropic1,177±2122,440—
30—gemini-1.5-flash-8b-001ClosedGoogle1,177±516,178—
31—gemma-2-9b-itOpenGoogle1,176±337,949—
32—gemini-pro-dev-apiClosedGoogle1,147±518,785—
33—llama-3-8b-instructOpenMeta1,142±3109,373—
34—gpt-3.5-turbo-0125ClosedOpenAI · 1 more variant1,137±368,889—
35—gemini-proClosedGoogle1,131±76,561—
36—llama-3.1-8b-instructOpenMeta1,129±339,806—
37—phi-3-medium-4k-instructOpenMicrosoft1,118±326,149—
38—dbrx-instruct-previewOpenDatabricks1,113±333,725—
39—gemma-2-2b-itOpenGoogle1,111±429,470—
40—wizardlm-70bOpenMicrosoft1,104±68,382—
41—snowflake-arctic-instructOpenSnowflake1,103±434,192—
42—phi-3-small-8k-instructOpenMicrosoft1,098±418,497—
43—gemma-1.1-7b-itOpenGoogle1,098±425,090—
44—llama-3.2-3b-instructOpenMeta1,093±78,467—
45—llama-2-70b-chatOpenMeta1,081±339,621—
46—llama2-70b-steerlm-chatOpenNVIDIA1,074±103,638—
47—phi-3-mini-4k-instruct-june-2024OpenMicrosoft1,068±612,881—
48—wizardlm-13bOpenMicrosoft1,063±87,185—
49—phi-3-mini-4k-instructOpenMicrosoft1,055±421,119—
50—llama-2-13b-chatOpenMeta1,053±419,727—

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 “—”.