The Open Weights
LatestModelsLeaderboardsUpcomingCompanies
Subscribe
The Open Weights

The daily record of open-source AI. New model releases, leaderboards, and what's coming next — written for people who ship.

Refreshed every 12 hours

Discover

  • Latest releases
  • New today
  • Trending models
  • Upcoming launches

Browse

  • All models
  • Companies
  • Categories
  • Leaderboards

About

  • About
  • Editorial policy
  • RSS feed
  • Newsletter

© 2026 The Open Weights. An independent publication.

Aggregated by Claude · written with Gemini · curated by humans.

Leaderboard

LLM Intelligence

Artificial Analysis Intelligence Index — a blended measure of reasoning, knowledge, and coding across open-weight and proprietary language models.

Source: Artificial Analysis · Updated Jun 17, 2026 · 20 models
LLM IntelligenceText-to-ImageImage EditingText-to-VideoImage-to-VideoText-to-SpeechOpen LLMMost DownloadedCommunity Favorites
#ModelIntelligence
1
GLM-5.2
Z AI
50.7
2
DeepSeek V4 Pro
DeepSeek
44.3
3
Kimi K2.6
Kimi
42.8
4
Kimi K2.7 Code
Kimi
41.9
5
DeepSeek V4 Flash
DeepSeek
40.3
6
GLM-5.1
Z AI
40.2
7
GLM-5
Z AI
39.5
8
Kimi K2.5
Kimi
38.1
9
Nemotron 3 Ultra 550B A55B
NVIDIA
37.8
10
Qwen3.6 27B
Qwen · Alibaba
37.1
11
GLM-4.7
Z AI
33.8
12
Qwen3.5 27B
Qwen · Alibaba
33.8
13
Qwen3.5 397B A17B
Qwen · Alibaba
33.7
14
DeepSeek V3.2
DeepSeek
33.4
15
Qwen3.6 35B A3B
Qwen · Alibaba
33.0
16
Kimi K2 Thinking
Kimi
32.7
17
Qwen3.5 122B A10B
Qwen · Alibaba
32.3
18
Gemma 4 31B
Google DeepMind
29.4
19
Qwen3.5 35B A3B
Qwen · Alibaba
29.3
20
DeepSeek V3.1 Terminus
DeepSeek
26.3

Leaderboard data is cached from Artificial Analysis and refreshed every 12 hours. Scores shown are for reference; see the source for full methodology.