Skip to content
IFAI

Model rankings

140 models · 1 boards · 1 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published December 5, 2024

Most preferred
o1-previewOpenAI1,302Score
Best open model
Best from China
yi-lightning01 AI1,246Score
Most voted
claude-3-opus-20240229Anthropic192,206Votes
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
3athene-v2-chatNexusFlow · #18 overall1,233
RankChangeModelScore95% intervalVotesPrice $/M
1—o1-previewClosedOpenAI1,302±430,448—
2—claude-3-5-sonnet-20241022ClosedAnthropic1,284±434,846—
3—gemini-1.5-pro-002ClosedGoogle1,268±432,758—
4—gpt-4o-2024-05-13ClosedOpenAI1,263±3116,858—
5—claude-3-5-sonnet-20240620ClosedAnthropic1,259±386,439—
6—o1-miniClosedOpenAI1,258±437,176—
7—gemini-advanced-0514ClosedGoogle1,254±352,216—
8—llama-3.1-405b-instruct-fp8OpenMeta1,252±357,468—
9—llama-3.1-405b-instruct-bf16OpenMeta1,252±514,541—
10▲ 1grok-2-2024-08-13ClosedxAI1,249±355,616—
11▼ 1gpt-4o-2024-08-06ClosedOpenAI1,249±347,053—
12—yi-lightningClosed01 AI1,246±429,193—
13—gpt-4-turbo-2024-04-09ClosedOpenAI1,242±3102,256—
14—gemini-1.5-pro-001ClosedGoogle1,240±382,557—
15—claude-3-opus-20240229ClosedAnthropic1,239±2192,206—
16—gpt-4-1106-previewClosedOpenAI1,234±2103,853—
17—glm-4-plusClosedZhipu AI1,234±428,006—
18—gpt-4o-mini-2024-07-18ClosedOpenAI1,233±354,539—
19—athene-v2-chatOpenNexusFlow1,233±58,700—
20—mistral-large-2407OpenMistral1,231±348,382—
21—gpt-4-0125-previewClosedOpenAI1,231±297,178—
22—qwen-max-0919OpenAlibaba1,231±417,587—
23—gemini-1.5-flash-002ClosedGoogle1,229±426,276—
24▲ 1deepseek-v2.5OpenDeepSeek1,225±326,517—
25▲ 1grok-2-mini-2024-08-13ClosedxAI1,223±447,339—
26▼ 2mistral-large-2411OpenMistral1,223±92,773—
27▲ 1qwen2.5-72b-instructOpenAlibaba1,223±431,639—
28▼ 1athene-70b-0725OpenNexusFlow1,222±420,660—
29—llama-3.1-nemotron-70b-instructOpenNVIDIA1,215±67,676—
30—llama-3.1-70b-instructOpenMeta1,213±353,577—
31—reka-core-20240904ClosedReka AI1,207±67,975—
32—gemma-2-27b-itOpenGoogle1,206±363,043—
33—jamba-1.5-largeOpenAI21 Labs1,204±69,146—
34—llama-3.1-nemotron-51b-instructOpenNVIDIA1,204±93,925—
35—gemini-1.5-flash-001ClosedGoogle1,204±365,753—
36—gpt-4-0314ClosedOpenAI1,200±355,979—
37—gemma-2-9b-it-simpoOpenPrinceton1,199±610,566—
38—claude-3-sonnet-20240229ClosedAnthropic1,197±3113,091—
39—command-r-plus-08-2024OpenCohere1,197±510,572—
40—nemotron-4-340b-instructOpenNVIDIA1,196±420,643—
41—llama-3-70b-instructOpenMeta1,195±2163,890—
42—reka-flash-20240904ClosedReka AI1,192±68,159—
43—qwen2.5-coder-32b-instructOpenAlibaba1,189±75,755—
44—glm-4-0520ClosedZhipu AI1,188±610,227—
45—gpt-4-0613ClosedOpenAI1,186±391,673—
46▲ 1c4ai-aya-expanse-32bOpenCohere1,183±518,402—
47▼ 1command-r-plusOpenCohere1,183±280,924—
48—deepseek-coder-v2OpenDeepSeek1,182±515,786—
49—qwen2-72b-instructOpenAlibaba1,181±438,960—
50▲ 1gemini-1.5-flash-8b-001ClosedGoogle1,179±427,858—

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 “—”.