Skip to content
IFAI

Model rankings

149 models · 1 boards · 1 sources

Artificial AnalysisIntelligence IndexArenaText arena

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

Most preferred
o1-previewOpenAI1,303Score
Best open model
Best from China
yi-lightning01 AI1,246Score
Most voted
claude-3-opus-20240229Anthropic198,375Votes
Top three by Score
1o1-previewOpenAI1,303
3gemini-1.5-pro-002Google1,268
Top three open models
1llama-3.1-405b-instruct-fp8Meta · #7 overall1,252
2llama-3.1-405b-instruct-bf16Meta · #8 overall1,252
3deepseek-v2.5-1210DeepSeek · #14 overall1,239
RankChangeModelScore95% intervalVotesPrice $/M
1—o1-previewClosedOpenAI1,303±333,259—
2—claude-3-5-sonnet-20241022ClosedAnthropic · 1 more variant1,285±440,938—
3—gemini-1.5-pro-002ClosedGoogle1,268±438,758—
4—gpt-4o-2024-05-13ClosedOpenAI1,263±3117,916—
5—o1-miniClosedOpenAI1,257±442,423—
6—gemini-advanced-0514ClosedGoogle1,254±352,193—
7—llama-3.1-405b-instruct-fp8OpenMeta1,252±363,247—
8—llama-3.1-405b-instruct-bf16OpenMeta1,252±514,927—
9—gpt-4o-2024-08-06ClosedOpenAI1,250±448,055—
10—grok-2-2024-08-13ClosedxAI1,249±360,980—
11—gpt-4-turbo-2024-04-09ClosedOpenAI1,242±3102,228—
12—gemini-1.5-pro-001ClosedGoogle1,241±382,551—
13—claude-3-opus-20240229ClosedAnthropic1,239±3198,375—
14▲ 1gpt-4o-mini-2024-07-18ClosedOpenAI1,235±357,421—
15▼ 1gpt-4-1106-previewClosedOpenAI1,235±3103,814—
16—llama-3.3-70b-instructOpenMeta1,234±78,907—
17—claude-3-5-haiku-20241022ClosedAnthropic1,234±74,961—
18—gpt-4-0125-previewClosedOpenAI1,231±397,142—
19—gemini-1.5-flash-002ClosedGoogle1,229±431,271—
20—grok-2-mini-2024-08-13ClosedxAI1,224±352,002—
21—llama-3.1-nemotron-70b-instructOpenNVIDIA1,216±77,667—
22—llama-3.1-70b-instructOpenMeta1,214±458,794—
23—gemma-2-27b-itOpenGoogle1,207±369,149—
24—amazon-nova-pro-v1.0ClosedAmazon1,207±67,485—
25—llama-3.1-nemotron-51b-instructOpenNVIDIA1,204±83,926—
26—gemini-1.5-flash-001ClosedGoogle1,204±365,728—
27—gpt-4-0314ClosedOpenAI1,200±355,976—
28—claude-3-sonnet-20240229ClosedAnthropic1,197±3113,091—
29—nemotron-4-340b-instructOpenNVIDIA1,196±420,649—
30—llama-3-70b-instructOpenMeta1,195±2163,878—
31—gpt-4-0613ClosedOpenAI1,185±391,652—
32—amazon-nova-lite-v1.0ClosedAmazon1,185±57,585—
33—gemini-1.5-flash-8b-001ClosedGoogle1,179±432,964—
34—gemma-2-9b-itOpenGoogle1,179±446,948—
35—claude-3-haiku-20240307ClosedAnthropic1,177±2122,422—
36—amazon-nova-micro-v1.0ClosedAmazon1,163±67,641—
37—gemini-pro-dev-apiClosedGoogle1,147±418,800—
38—llama-3-8b-instructOpenMeta1,143±3109,267—
39—gpt-3.5-turbo-0125ClosedOpenAI · 1 more variant1,137±368,891—
40—llama-3.1-8b-instructOpenMeta1,133±352,712—
41—gemini-proClosedGoogle1,131±86,560—
42—phi-3-medium-4k-instructOpenMicrosoft1,118±426,122—
43—gemma-2-2b-itOpenGoogle1,116±438,514—
44—dbrx-instruct-previewOpenDatabricks1,113±333,738—
45—granite-3.0-8b-instructOpenIBM1,110±87,068—
46—wizardlm-70bOpenMicrosoft1,105±78,381—
47—snowflake-arctic-instructOpenSnowflake1,102±334,181—
48—gemma-1.1-7b-itOpenGoogle1,099±425,072—
49—phi-3-small-8k-instructOpenMicrosoft1,098±418,503—
50—llama-3.2-3b-instructOpenMeta1,094±78,423—

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 “—”.