Intelligence Index benchmark

411 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 Fable 5 (Anthropic) leads at 59.9, from $10.00 per 1M input.

Data via Artificial Analysis methodology

Models ranked

411

on this benchmark

Top score

59.9

current leader

Type

Composite

index

Updated

15 July 2026

last source fetch

Cost vs Intelligence Index

211 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 · 411 models
Maker
#
1Claude Fable 5Anthropic59.9$10.00$50.00
2GPT-5.6 SolOpenAI58.9$5.00$30.00
3Claude Opus 4.8Anthropic55.7$5.00$25.00
4GPT-5.6 TerraOpenAI55.0$2.50$15.00
5GPT-5.5OpenAI54.8$5.00$30.00
6Grok 4.5xAI53.8$2.00$6.00
7Claude Opus 4.7Anthropic53.5$5.00$25.00
8Claude Sonnet 5Anthropic53.4$2.00$10.00
9GPT-5.4OpenAI51.4$2.50$15.00
10GPT-5.6 LunaOpenAI51.2$1.00$6.00
11GLM 5.2Zhipu51.1$1.40$4.40
12Muse Spark 1.1Other50.6$1.25$4.25
13Gemini 3.5 FlashGoogle50.2$1.50$9.00
14Claude Sonnet 4.6Anthropic47.2reasoning: adaptive$3.00$15.00
15Gemini 3.1 Pro PreviewGoogle46.5$2.00$12.00
16Qwen3.7 MaxAlibaba46.0n/an/a
17MiniMax M3MiniMax44.4$0.30$1.20
18DeepSeek V4 ProDeepSeek44.3$0.43$0.87
19GPT-5.3 CodexOpenAI44.3n/an/a
20Kimi K2.6Moonshot44.2n/an/a
21Claude Opus 4.6Anthropic43.7reasoning: adaptive$5.00$25.00
22Muse SparkMeta43.1n/an/a
23MiMo-V2.5-ProXiaomi42.2$1.00$3.00
24GPT-5.2OpenAI42.2$1.75$14.00
25Kimi K2.7 CodeMoonshot41.9$0.95$4.00
26Hy3-previewTencent41.2n/an/a
27Nex-N2-ProNex-agi41.0n/an/a
28Claude Opus 4.5Anthropic40.8reasoning: true$5.00$25.00
29MiMo-V2-ProXiaomi40.3n/an/a
30DeepSeek V4 FlashDeepSeek40.3n/an/a
31GLM 5.1Zhipu40.2$1.05$3.50
32GPT-5.2-CodexOpenAI40.1$1.75$14.00
33Qwen3.6 Max PreviewAlibaba40n/an/a
34GPT-5.4 MiniOpenAI40.0$0.75$4.50
35Grok Build 0.1 0616Spacexai39.8n/an/a
36Qwen3.6 PlusAlibaba39.6$0.33$1.95
37Gemini 3 ProGoogle39.6$2.00$12.00
38GLM 5Zhipu39.5$0.80$2.56
39Qwen3.7 PlusAlibaba39.0n/an/a
40JT-4.1 Flash 236B A21BChina-mobile38.8n/an/a
41GPT-5.4 NanoOpenAI38.2$0.20$1.25
42MiniMax M2.7MiniMax38.1$0.26$0.55
43GLM-5-TurboZhipu38.1n/an/a
44Nemotron 3 UltraNVIDIA37.8n/an/a
45Gemini 3 FlashGoogle37.8reasoning: truen/an/a
46Grok 4.3xAI37.6$1.25$2.50
47MiMo-V2.5Xiaomi37.2n/an/a
48Qwen3.6 27BAlibaba37.1$0.15$0.50
49Grok 4.20 0309 v2Spacexai37n/an/a
50GPT-5.1OpenAI36.9$1.25$10.00
150 of 411
Page 1 of 9
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 Fable 5 (Anthropic) leads with 59.9, from $10.00 per 1M input tokens.

How many models are ranked on Intelligence Index?

411 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 15 July 2026

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI