Skip to content
IFAI

Model rankings

141 models · 1 boards · 1 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published December 1, 2024

Most preferred
o1-previewOpenAI1,301Score
Best open model
Best from China
yi-lightning01 AI1,245Score
Most voted
claude-3-opus-20240229Anthropic190,685Votes
Top three by Score
1o1-previewOpenAI1,301
3gemini-1.5-pro-002Google1,267
Top three open models
1llama-3.1-405b-instruct-fp8Meta · #7 overall1,253
2llama-3.1-405b-instruct-bf16Meta · #8 overall1,252
3athene-v2-chatNexusFlow · #18 overall1,232
RankChangeModelScore95% intervalVotesPrice $/M
1—o1-previewClosedOpenAI1,301±429,747—
2—claude-3-5-sonnet-20241022ClosedAnthropic · 1 more variant1,284±433,295—
3—gemini-1.5-pro-002ClosedGoogle1,267±431,240—
4—gpt-4o-2024-05-13ClosedOpenAI1,263±3115,598—
5—o1-miniClosedOpenAI1,258±435,691—
6—gemini-advanced-0514ClosedGoogle1,254±352,216—
7—llama-3.1-405b-instruct-fp8OpenMeta1,253±356,051—
8—llama-3.1-405b-instruct-bf16OpenMeta1,252±514,541—
9—gpt-4o-2024-08-06ClosedOpenAI1,249±346,335—
10—grok-2-2024-08-13ClosedxAI1,249±354,702—
11—gpt-4-turbo-2024-04-09ClosedOpenAI1,242±3102,256—
12—gemini-1.5-pro-001ClosedGoogle1,240±382,552—
13—claude-3-opus-20240229ClosedAnthropic1,238±2190,685—
14—gpt-4-1106-previewClosedOpenAI1,234±2103,865—
15—gpt-4o-mini-2024-07-18ClosedOpenAI1,233±453,789—
16—gpt-4-0125-previewClosedOpenAI1,231±397,210—
17—gemini-1.5-flash-002ClosedGoogle1,228±424,792—
18—grok-2-mini-2024-08-13ClosedxAI1,224±445,929—
19—llama-3.1-nemotron-70b-instructOpenNVIDIA1,215±67,675—
20—llama-3.1-70b-instructOpenMeta1,213±452,009—
21—gemma-2-27b-itOpenGoogle1,206±461,424—
22—llama-3.1-nemotron-51b-instructOpenNVIDIA1,204±93,924—
23—gemini-1.5-flash-001ClosedGoogle1,204±365,763—
24—gpt-4-0314ClosedOpenAI1,200±355,980—
25—claude-3-sonnet-20240229ClosedAnthropic1,197±2113,103—
26—nemotron-4-340b-instructOpenNVIDIA1,196±420,646—
27—llama-3-70b-instructOpenMeta1,195±3163,906—
28—gpt-4-0613ClosedOpenAI1,186±391,679—
29—gemma-2-9b-itOpenGoogle1,178±343,070—
30▲ 1gemini-1.5-flash-8b-001ClosedGoogle1,177±426,266—
31▼ 1claude-3-haiku-20240307ClosedAnthropic1,177±2122,419—
32—gemini-pro-dev-apiClosedGoogle1,147±518,800—
33—llama-3-8b-instructOpenMeta1,142±3109,332—
34—gpt-3.5-turbo-0125ClosedOpenAI · 1 more variant1,137±368,903—
35—gemini-proClosedGoogle1,131±76,563—
36—llama-3.1-8b-instructOpenMeta1,131±348,770—
37—phi-3-medium-4k-instructOpenMicrosoft1,118±326,135—
38▲ 1gemma-2-2b-itOpenGoogle1,113±434,623—
39▼ 1dbrx-instruct-previewOpenDatabricks1,113±333,753—
40—granite-3.0-8b-instructOpenIBM1,110±87,072—
41—wizardlm-70bOpenMicrosoft1,105±68,386—
42—snowflake-arctic-instructOpenSnowflake1,103±334,183—
43—phi-3-small-8k-instructOpenMicrosoft1,098±418,506—
44—gemma-1.1-7b-itOpenGoogle1,098±325,092—
45—llama-3.2-3b-instructOpenMeta1,093±78,434—
46—granite-3.0-2b-instructOpenIBM1,082±77,247—
47—llama-2-70b-chatOpenMeta1,081±339,648—
48—llama2-70b-steerlm-chatOpenNVIDIA1,074±103,638—
49—phi-3-mini-4k-instruct-june-2024OpenMicrosoft1,068±612,855—
50—wizardlm-13bOpenMicrosoft1,063±87,183—

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 “—”.