Skip to content
IFAI

Model rankings

147 models · 1 boards · 1 sources

Artificial AnalysisIntelligence IndexArenaText arena

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

Most preferred
o1-previewOpenAI1,302Score
Best open model
Best from China
yi-lightning01 AI1,246Score
Most voted
claude-3-opus-20240229Anthropic196,315Votes
Top three by Score
1o1-previewOpenAI1,302
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
3llama-3.3-70b-instructMeta · #18 overall1,234
RankChangeModelScore95% intervalVotesPrice $/M
1—o1-previewClosedOpenAI1,302±332,251—
2—claude-3-5-sonnet-20241022ClosedAnthropic · 1 more variant1,284±338,982—
3—gemini-1.5-pro-002ClosedGoogle1,268±436,776—
4—gpt-4o-2024-05-13ClosedOpenAI1,263±2117,989—
5—o1-miniClosedOpenAI1,258±340,568—
6—gemini-advanced-0514ClosedGoogle1,254±352,201—
7—llama-3.1-405b-instruct-fp8OpenMeta1,252±361,518—
8—llama-3.1-405b-instruct-bf16OpenMeta1,252±514,535—
9▲ 1gpt-4o-2024-08-06ClosedOpenAI1,250±348,165—
10▼ 1grok-2-2024-08-13ClosedxAI1,249±359,097—
11—gpt-4-turbo-2024-04-09ClosedOpenAI1,242±3102,237—
12—gemini-1.5-pro-001ClosedGoogle1,241±382,565—
13—claude-3-opus-20240229ClosedAnthropic1,239±2196,315—
14—gpt-4-1106-previewClosedOpenAI1,235±3103,840—
15—gpt-4o-mini-2024-07-18ClosedOpenAI1,234±356,415—
16Newllama-3.3-70b-instructOpenMeta1,234±77,647—
17Newclaude-3-5-haiku-20241022ClosedAnthropic1,233±94,179—
18▼ 2gpt-4-0125-previewClosedOpenAI1,231±397,157—
19▼ 2gemini-1.5-flash-002ClosedGoogle1,229±430,208—
20▼ 2grok-2-mini-2024-08-13ClosedxAI1,224±351,012—
21▼ 2llama-3.1-nemotron-70b-instructOpenNVIDIA1,216±57,672—
22▼ 2llama-3.1-70b-instructOpenMeta1,214±357,780—
23▼ 2gemma-2-27b-itOpenGoogle1,207±367,092—
24Newamazon-nova-pro-v1.0ClosedAmazon1,207±76,195—
25▼ 3llama-3.1-nemotron-51b-instructOpenNVIDIA1,204±83,928—
26▼ 3gemini-1.5-flash-001ClosedGoogle1,204±365,728—
27▼ 3gpt-4-0314ClosedOpenAI1,200±355,980—
28▼ 3claude-3-sonnet-20240229ClosedAnthropic1,197±2113,091—
29▼ 3nemotron-4-340b-instructOpenNVIDIA1,196±420,648—
30▼ 3llama-3-70b-instructOpenMeta1,195±2163,884—
31▼ 3gpt-4-0613ClosedOpenAI1,185±391,660—
32Newamazon-nova-lite-v1.0ClosedAmazon1,184±76,238—
33▼ 4gemini-1.5-flash-8b-001ClosedGoogle1,179±331,868—
34▼ 4gemma-2-9b-itOpenGoogle1,179±345,891—
35▼ 4claude-3-haiku-20240307ClosedAnthropic1,177±3122,408—
36Newamazon-nova-micro-v1.0ClosedAmazon1,163±76,259—
37▼ 5gemini-pro-dev-apiClosedGoogle1,147±518,798—
38▼ 5llama-3-8b-instructOpenMeta1,143±2109,298—
39▼ 5gpt-3.5-turbo-0125ClosedOpenAI · 1 more variant1,137±368,882—
40▼ 5llama-3.1-8b-instructOpenMeta1,133±351,800—
41▼ 5gemini-proClosedGoogle1,131±86,560—
42▼ 5phi-3-medium-4k-instructOpenMicrosoft1,118±426,130—
43▼ 5gemma-2-2b-itOpenGoogle1,115±437,482—
44▼ 5dbrx-instruct-previewOpenDatabricks1,113±333,745—
45▼ 5granite-3.0-8b-instructOpenIBM1,110±87,068—
46▼ 5wizardlm-70bOpenMicrosoft1,105±78,383—
47▼ 5snowflake-arctic-instructOpenSnowflake1,102±334,177—
48▼ 5gemma-1.1-7b-itOpenGoogle1,099±325,080—
49▼ 5phi-3-small-8k-instructOpenMicrosoft1,098±418,501—
50▼ 5llama-3.2-3b-instructOpenMeta1,093±78,427—

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 “—”.