Skip to content
IFAI

Model rankings

115 models · 1 boards · 1 sources

Artificial AnalysisIntelligence IndexArenaText arena

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

Most preferred
gpt-4o-2024-05-13OpenAI1,262Score
Best open model
Best from China
deepseek-v2.5DeepSeek1,219Score
Most voted
claude-3-opus-20240229Anthropic164,812Votes
Top three by Score
1gpt-4o-2024-05-13OpenAI1,262
Top three open models
1llama-3.1-405b-instruct-bf16Meta · #4 overall1,251
2llama-3.1-405b-instruct-fp8Meta · #5 overall1,250
3mistral-large-2407Mistral · #14 overall1,229
RankChangeModelScore95% intervalVotesPrice $/M
1▲ 1gpt-4o-2024-05-13ClosedOpenAI1,262±390,035—
2▲ 1claude-3-5-sonnet-20240620ClosedAnthropic1,259±361,859—
3▲ 1gemini-advanced-0514ClosedGoogle1,251±352,221—
4Newllama-3.1-405b-instruct-bf16OpenMeta1,251±75,516—
5Newllama-3.1-405b-instruct-fp8OpenMeta1,250±430,608—
6—grok-2-2024-08-13ClosedxAI1,249±423,048—
7—gpt-4o-2024-08-06ClosedOpenAI1,247±421,825—
8—gpt-4-turbo-2024-04-09ClosedOpenAI1,241±292,633—
9—claude-3-opus-20240229ClosedAnthropic1,238±2164,812—
10—gemini-1.5-pro-api-0514ClosedGoogle1,237±379,955—
11—gpt-4-1106-previewClosedOpenAI1,234±297,025—
12—gpt-4o-mini-2024-07-18ClosedOpenAI1,230±329,755—
13—gpt-4-0125-previewClosedOpenAI1,230±390,197—
14—mistral-large-2407OpenMistral1,229±426,170—
15—grok-2-mini-2024-08-13ClosedxAI1,220±521,038—
16—athene-70b-0725OpenNexusFlow1,220±420,300—
17Newdeepseek-v2.5OpenDeepSeek1,219±84,227—
18▼ 1llama-3.1-70b-instructOpenMeta1,210±525,551—
19▼ 1gemma-2-27b-itOpenGoogle1,203±436,824—
20▲ 1jamba-1.5-largeOpenAI21 Labs1,201±69,185—
21▼ 1gemini-1.5-flash-api-0514ClosedGoogle1,201±364,438—
22▼ 3gpt-4-0314ClosedOpenAI1,200±355,944—
23▲ 1gemma-2-9b-it-simpoOpenPrinceton1,197±510,624—
24▼ 2claude-3-sonnet-20240229ClosedAnthropic1,197±3113,043—
25▼ 2nemotron-4-340b-instructOpenNVIDIA1,196±420,647—
26▼ 1llama-3-70b-instructOpenMeta1,193±2163,861—
27▼ 1command-r-plus-08-2024OpenCohere1,192±94,975—
28▼ 1glm-4-0520ClosedZhipu AI1,187±710,233—
29▼ 1gpt-4-0613ClosedOpenAI1,186±391,633—
30▼ 1command-r-plusOpenCohere1,182±380,861—
31—qwen2-72b-instructOpenAlibaba1,181±338,961—
32▼ 2deepseek-coder-v2OpenDeepSeek1,180±415,796—
33▼ 1claude-3-haiku-20240307ClosedAnthropic1,176±2114,426—
34▼ 1gemma-2-9b-itOpenGoogle1,173±429,883—
35▼ 1command-r-08-2024OpenCohere1,169±85,133—
36▼ 1mistral-large-2402ClosedMistral1,158±364,923—
37—jamba-1.5-miniOpenAI21 Labs1,156±69,311—
38▼ 2qwen1.5-110b-chatOpenAlibaba1,155±327,459—
39▼ 1reka-flash-21b-20240226-onlineClosedReka AI1,151±416,028—
40▼ 1mixtral-8x22b-instruct-v0.1OpenMistral1,149±253,813—
41▼ 1qwen1.5-72b-chatOpenAlibaba1,148±440,614—
42▼ 1command-rOpenCohere1,147±356,361—
43▼ 1gemini-pro-dev-apiClosedGoogle1,147±418,776—
44▼ 1mistral-mediumClosedMistral1,141±435,538—
45—reka-flash-21b-20240226ClosedReka AI1,141±425,800—
46▼ 2llama-3-8b-instructOpenMeta1,141±2111,021—
47▼ 1gpt-3.5-turbo-0125ClosedOpenAI1,138±368,860—
48—yi-1.5-34b-chatOpen01 AI1,132±325,148—
49▼ 2gemini-proClosedGoogle1,132±86,556—
50▼ 1zephyr-orpo-141b-A35b-v0.1OpenHuggingFace1,131±84,852—

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 “—”.