Intelligence Index benchmark

453 AI models ranked on Intelligence Index. Each row shows the model’s score next to its cheapest API price per 1M tokens where it has one, so you can weigh quality against cost.

Top model today

Claude Opus 5 (Anthropic) leads at 63.1, from $5.00 per 1M input.

Data via Artificial Analysis methodology

Models ranked

453

on this benchmark

Top score

63.1

current leader

Type

Composite

index

Updated

30 Aug 2026

last source fetch

Cost vs Intelligence Index

263 priced models
Most attractive quadrant (cheap + high)
= reasoning model (extended thinking)

Each labelled name links to that model’s page. Curated to the cost-efficiency frontier, top scorers and cheapest so labels stay readable; the full field is in the leaderboard table below (and via “select all”). Reasoning models (extended “thinking” before answering) carry a ring around the dot.

Models ranked on Intelligence Index

highest score first · 453 models
Maker
#
1Claude Opus 5Anthropic63.1$5.00$25.00
2Claude Fable 5Anthropic62.1$10.00$50.00
3GPT-5.6 SolOpenAI60.9$2.00$10.00
4Grok 4.6xAI60.9$2.00$6.00
5Kimi K3Moonshot59.7$2.85$14.25
6GLM 5.3Zhipu59.5$1.40$4.40
7Qwen3.8 MaxAlibaba58.1$1.65$4.95
8Qwen3.8 2.4T A95BAlibaba57.7$2.00$6.00
9GLM 5.3 FlashZhipu57.5$0.07$0.25
10Claude Opus 4.8Anthropic57.3$5.00$25.00
11Muse Spark 1.2Other56.8$1.25$4.25
12GPT-5.6 TerraOpenAI56.6$2.00$12.00
13GPT-5.5OpenAI56.3$5.00$30.00
14Gemini 3.7 FlashGoogle56.0$0.75$3.75
15Qwen3.8-Flash-NextAlibaba55.8n/an/a
16Grok 4.5xAI55.8$2.00$6.00
17Claude Sonnet 5Anthropic55.3$2.00$10.00
18Claude Opus 4.7Anthropic55.0$5.00$25.00
19Muse Spark 1.1Other53.2$1.25$4.25
20DeepSeek V4 Pro 0423DeepSeek53.2$0.43$0.87
21GPT-5.4OpenAI53.1$2.50$15.00
22GLM 5.2Zhipu52.6$0.61$1.98
23GPT-5.6 LunaOpenAI52.3$0.20$1.20
24Qwen3.8 27BAlibaba52.0$0.40$2.55
25Gemini 3.5 FlashGoogle52.0$1.50$9.00
26DeepSeek V4 Flash 0423DeepSeek51.8$0.08$0.17
27Gemini 3.6 FlashGoogle51.6$0.75$3.75
28DeepSeek V4 Flash Vision (Reasoning, Max Effort)DeepSeek51.5n/an/a
29Agnes 2.5 Pro BetaSapiens-ai49.1n/an/a
30Claude Sonnet 4.6Anthropic48.4reasoning: adaptive$3.00$15.00
31Gemini 3.1 Pro PreviewGoogle47.7$2.00$12.00
32Motif 3Motif-technologies47.4n/an/a
33Qwen3.7 MaxAlibaba46.7$1.25$3.75
34GPT-5.3-CodexOpenAI45.5$1.75$14.00
35MiniMax M3MiniMax45.4$0.23$0.96
36Motif 3 (Beta)Motif-technologies45.3n/an/a
37DeepSeek V4 Pro (max)DeepSeek45.3n/an/a
38Kimi K2.6Moonshot45.1$0.65$3.40
39Claude Opus 4.6Anthropic44.9reasoning: adaptive$5.00$25.00
40Muse SparkMeta44.3n/an/a
41GPT-5.2OpenAI43.3$1.75$14.00
42Kimi K2.7 CodeMoonshot43.0$0.66$3.40
43MiMo-V2.5-ProXiaomi42.9$0.43$0.87
44InklingOther42.3$0.95$4.05
45Hy3Other42.2$0.13$0.53
46DeepSeek V4 Flash (max)DeepSeek42.1n/an/a
47Claude Opus 4.5Anthropic41.9reasoning: true$5.00$25.00
48Nex-N2-ProOther41.7$0.25$1.00
49Solar Pro 4Other41.6$0.03$0.12
50MiMo-V2-ProXiaomi41.4n/an/a
150 of 453
Page 1 of 10
Prices are on-demand list rates. Enterprise commitments can be materially lower. Cost per task uses best-effort token usage.

Frequently asked questions

What is the Intelligence Index benchmark?

Artificial Analysis's headline composite score (0 to 100) that combines many independent evaluations across reasoning, knowledge, science, coding and agentic tasks into a single number, each run independently by Artificial Analysis. The exact component evals and their weights are versioned by Artificial Analysis; see their methodology for the current makeup.

Which AI model scores highest on Intelligence Index?

Claude Opus 5 (Anthropic) leads with 63.1, from $5.00 per 1M input tokens.

How many models are ranked on Intelligence Index?

453 models carry a Intelligence Index score. Scores come from Artificial Analysis; where a model has a live API price it is verified against LiteLLM and OpenRouter, and models with no current price are listed without one.

Other benchmarks

compare the same models on a different eval
Benchmark scores via Artificial Analysis · pricing verified against LiteLLM + OpenRouter · refreshed daily · updated 30 Aug 2026

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI