Skip to content

Intelligence Index 2026

Objective benchmark comparisons for the world's leading LLMs. Updated weekly as new models and variants are released.

Data last verified: July 18, 2026 · 576 model variants tracked

License Type
Showing 576 of 576 models
AI Model Intelligence Index 2026 — benchmark comparison of 576 LLM variants across Code Arena, Chat Arena, GPQA Diamond, SWE-Bench, and ARC-AGI-2 metrics
#
Model
Price
01
59.9%163176.5%$20.00 / 1M tokens
02
58.9%77.4%$11.25 / 1M tokens
03
57.7%78.3%$11.25 / 1M tokens
04
57.1%167976.2%$6.00 / 1M tokens
05
55.9%77.2%$11.25 / 1M tokens
06
55.7%153474.3%$10.00 / 1M tokens
07
55%76.7%$5.63 / 1M tokens
08
54.8%74.9%$11.25 / 1M tokens
09
53.8%155872.4%$3.00 / 1M tokens
10
53.6%76.3%$11.25 / 1M tokens
11
53.5%155573.6%$10.00 / 1M tokens
12
53.4%154271.5%$4.00 / 1M tokens
13
53.1%71.6%$11.25 / 1M tokens
14
51.6%70.6%$5.63 / 1M tokens
15
51.4%71.1%$5.63 / 1M tokens
16
51.2%71.4%$2.25 / 1M tokens
17
51.1%158768.8%$2.15 / 1M tokens
18
50.6%153871.3%$2.00 / 1M tokens
19
50.4%71.5%$11.25 / 1M tokens
20
50.2%150470.1%$3.38 / 1M tokens
Page 1 of 29 | 576 models total
...

Complete AI Comparison Library

Deep-dive into technical performance metrics and head-to-head architectural analysis for all leading AI models.

94Comparisons Available