Skip to content
IFAI

Model rankings

128 models · 1 boards · 1 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published October 23, 2024

Most preferred
o1-previewOpenAI1,303Score
Best open model
Best from China
yi-lightning01 AI1,241Score
Most voted
claude-3-opus-20240229Anthropic176,723Votes
Top three by Score
1o1-previewOpenAI1,303
2gemini-1.5-pro-002Google1,268
3gpt-4o-2024-05-13OpenAI1,261
Top three open models
1llama-3.1-405b-instruct-fp8Meta · #7 overall1,251
2llama-3.1-405b-instruct-bf16Meta · #8 overall1,251
3mistral-large-2407Mistral · #19 overall1,230
RankChangeModelScore95% intervalVotesPrice $/M
1—llama-3.1-405b-instruct-fp8OpenMeta1,251±241,936—
2—llama-3.1-405b-instruct-bf16OpenMeta1,251±414,603—
3—mistral-large-2407OpenMistral1,230±338,220—
4—qwen-max-0919OpenAlibaba1,229±514,223—
5▲ 1qwen2.5-72b-instructOpenAlibaba1,221±416,223—
6▼ 1deepseek-v2.5OpenDeepSeek1,221±416,478—
7—athene-70b-0725OpenNexusFlow1,221±420,703—
8—llama-3.1-70b-instructOpenMeta1,211±337,455—
9Newllama-3.1-nemotron-70b-instructOpenNVIDIA1,210±74,416—
10▼ 1gemma-2-27b-itOpenGoogle1,205±348,605—
11▼ 1jamba-1.5-largeOpenAI21 Labs1,203±69,185—
12▼ 1gemma-2-9b-it-simpoOpenPrinceton1,198±610,624—
13—command-r-plus-08-2024OpenCohere1,196±510,603—
14▼ 2nemotron-4-340b-instructOpenNVIDIA1,196±420,653—
15▼ 1llama-3-70b-instructOpenMeta1,194±2163,966—
16▼ 1command-r-plusOpenCohere1,183±380,917—
17—deepseek-coder-v2OpenDeepSeek1,181±515,803—
18▼ 2qwen2-72b-instructOpenAlibaba1,180±338,986—
19▼ 1gemma-2-9b-itOpenGoogle1,176±335,939—
20▼ 1command-r-08-2024OpenCohere1,175±510,941—
21▼ 1jamba-1.5-miniOpenAI21 Labs1,158±69,300—
22▼ 1qwen1.5-110b-chatOpenAlibaba1,155±327,475—
23▼ 1mixtral-8x22b-instruct-v0.1OpenMistral1,149±353,850—
24—command-rOpenCohere1,148±256,398—
25▼ 2qwen1.5-72b-chatOpenAlibaba1,148±340,640—
26▼ 1llama-3-8b-instructOpenMeta1,142±2109,383—
27▼ 1yi-1.5-34b-chatOpen01 AI1,132±425,150—
28▼ 1zephyr-orpo-141b-A35b-v0.1OpenHuggingFace1,131±84,858—
29—llama-3.1-8b-instructOpenMeta1,128±435,652—
30▼ 2qwen1.5-32b-chatOpenAlibaba1,127±322,779—
31▼ 1phi-3-medium-4k-instructOpenMicrosoft1,118±426,155—
32▲ 1internlm2_5-20b-chatOpenInternLM1,115±610,710—
33▼ 2mixtral-8x7b-instruct-v0.1OpenMistral1,114±076,158—
34▼ 2dbrx-instruct-previewOpenDatabricks1,113±333,736—
35▼ 1gemma-2-2b-itOpenGoogle1,109±427,446—
36▼ 1qwen1.5-14b-chatOpenAlibaba1,107±418,678—
37▼ 1wizardlm-70bOpenMicrosoft1,105±68,383—
38▼ 1snowflake-arctic-instructOpenSnowflake1,103±434,194—
39—yi-34b-chatOpen01 AI1,101±515,927—
40▼ 2openchat-3.5-0106OpenOpenChat · 1 more variant1,100±512,976—
41▼ 1phi-3-small-8k-instructOpenMicrosoft1,098±418,503—
42▼ 1gemma-1.1-7b-itOpenGoogle1,098±425,087—
43▲ 2llama-3.2-3b-instructOpenMeta1,093±78,453—
44—tulu-2-dpo-70bOpenAllenAI/UW1,092±76,666—
45▼ 3vicuna-33bOpenLMSYS1,091±422,942—
46—deepseek-llm-67b-chatOpenDeepSeek1,091±94,982—
47▼ 4starling-lm-7b-betaOpenNexusflow1,091±416,672—
48▼ 1openhermes-2.5-mistral-7bOpenNousResearch1,090±75,094—
49▼ 1starling-lm-7b-alphaOpenUC Berkeley1,083±610,414—
50▼ 1llama-2-70b-chatOpenMeta1,081±339,636—

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 “—”.