Skip to content
IFAI

Model rankings

167 models · 2 boards · 1 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published January 24, 2025

Most preferred
o1-2024-12-17OpenAI1,323Score
Best open model
deepseek-r1DeepSeek1,316Score
Best from China
deepseek-r1DeepSeek1,316Score
Most voted
claude-3-opus-20240229Anthropic202,713Votes
Top three by Score
1o1-2024-12-17OpenAI1,323
2deepseek-r1DeepSeek1,316
3o1-previewOpenAI1,303
Top three open models
1deepseek-r1DeepSeek · #2 overall1,316
2deepseek-v3DeepSeek · #5 overall1,276
3llama-3.1-405b-instruct-bf16Meta · #9 overall1,254
RankChangeModelScore95% intervalVotesPrice $/M
1Newdeepseek-r1OpenDeepSeek1,316±131,883—
2▼ 1deepseek-v3OpenDeepSeek1,276±613,640—
3▼ 1llama-3.1-405b-instruct-bf16OpenMeta1,254±422,703—
4▼ 1llama-3.1-405b-instruct-fp8OpenMeta1,253±363,187—
5▼ 1deepseek-v2.5-1210OpenDeepSeek · 1 more variant1,240±67,261—
6▼ 1llama-3.3-70b-instructOpenMeta1,235±516,905—
7▼ 1athene-v2-chatOpenNexusFlow1,232±422,355—
8▼ 1mistral-large-2407OpenMistral · 1 more variant1,232±348,205—
9▼ 1qwen-max-0919OpenAlibaba1,231±517,434—
10▼ 1athene-70b-0725OpenNexusFlow1,223±420,609—
11▼ 1qwen2.5-72b-instructOpenAlibaba1,223±340,664—
12▼ 1llama-3.1-nemotron-70b-instructOpenNVIDIA1,217±67,598—
13▼ 1llama-3.1-70b-instructOpenMeta1,214±358,785—
14▼ 1llama-3.1-tulu-3-70bOpenAi21,209±103,031—
15▼ 1gemma-2-27b-itOpenGoogle1,208±373,168—
16▼ 1jamba-1.5-largeOpenAI21 Labs1,205±79,125—
17▼ 1llama-3.1-nemotron-51b-instructOpenNVIDIA1,204±83,898—
18▼ 1gemma-2-9b-it-simpoOpenPrinceton1,200±610,551—
19▼ 1command-r-plus-08-2024OpenCohere1,198±510,541—
20▼ 1nemotron-4-340b-instructOpenNVIDIA1,196±420,604—
21▼ 1llama-3-70b-instructOpenMeta1,195±2163,809—
22▼ 1qwen2.5-coder-32b-instructOpenAlibaba1,190±85,730—
23▼ 1c4ai-aya-expanse-32bOpenCohere1,185±427,764—
24—phi-4OpenMicrosoft1,184±84,039—
25▼ 2command-r-plusOpenCohere1,183±380,852—
26▼ 1deepseek-coder-v2OpenDeepSeek1,182±415,754—
27▼ 1qwen2-72b-instructOpenAlibaba1,181±338,880—
28▼ 1gemma-2-9b-itOpenGoogle1,180±350,951—
29▼ 1command-r-08-2024OpenCohere1,176±510,846—
30▼ 1jamba-1.5-miniOpenAI21 Labs1,160±69,270—
31▼ 1ministral-8b-2410OpenMistral1,160±85,114—
32▼ 1qwen1.5-110b-chatOpenAlibaba1,156±427,466—
33▼ 1c4ai-aya-expanse-8bOpenCohere1,151±69,571—
34▼ 1mixtral-8x22b-instruct-v0.1OpenMistral1,149±353,787—
35▼ 1qwen1.5-72b-chatOpenAlibaba1,148±340,630—
36▼ 1command-rOpenCohere1,148±356,375—
37▼ 1llama-3.1-tulu-3-8bOpenAi21,147±103,079—
38▼ 1llama-3-8b-instructOpenMeta1,143±2109,237—
39▲ 1granite-3.1-8b-instructOpenIBM1,135±93,064—
40▼ 2yi-1.5-34b-chatOpen01 AI1,133±425,126—
41▼ 2llama-3.1-8b-instructOpenMeta1,133±352,651—
42▼ 1zephyr-orpo-141b-A35b-v0.1OpenHuggingFace1,130±84,863—
43▼ 1qwen1.5-32b-chatOpenAlibaba1,127±422,759—
44▼ 1phi-3-medium-4k-instructOpenMicrosoft1,118±426,110—
45▼ 1gemma-2-2b-itOpenGoogle1,117±342,631—
46▼ 1internlm2_5-20b-chatOpenInternLM1,116±510,595—
47▼ 1mixtral-8x7b-instruct-v0.1OpenMistral1,114±076,133—
48▼ 1dbrx-instruct-previewOpenDatabricks1,113±433,730—
49▼ 1granite-3.0-8b-instructOpenIBM1,110±87,002—
50▼ 1qwen1.5-14b-chatOpenAlibaba1,107±518,675—

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 “—”.