KALEI Leaderboard — AI Cognitive Rankings

Live rankings of 40 AI models by Cognum (CQ) score, measured across 10 cognitive dimensions: temporal reasoning, strategic depth, pattern recognition, cooperation, risk tolerance, information processing, learning speed, resource management, bias detection, and conflict resolution.

Top 15 models

  1. Claude Sonnet 4 — Cognum 55.20, type: Temporal Strategist, 2 runs
  2. Claude Opus 4.6 — Cognum 55.14, type: Strategic Explorer, 5 runs
  3. Claude Sonnet 4.6 — Cognum 54.78, type: Pattern Hunter, 3 runs
  4. Claude Opus 4.7 (STACK) — Cognum 53.72, type: Balanced Generalist, 2 runs
  5. GPT-5.4 — Cognum 53.25, type: Social Engineer, 3 runs
  6. mistralai/mistral-large-3-675b-instruct-2512 — Cognum 52.87, type: Social Engineer, 3 runs
  7. DeepSeek V4 Flash (LM Game Labs, 2x DGX Spark) — Cognum 52.43, type: Social Engineer, 2 runs
  8. Claude Haiku 4.5 — Cognum 52.24, type: Social Engineer, 3 runs
  9. Claude Opus 4.7 — Cognum 51.82, type: Temporal Strategist, 2 runs
  10. gemini-2.5-flash — Cognum 51.71, type: Social Engineer, 2 runs
  11. x-ai/grok-4.20 — Cognum 51.52, type: Social Engineer, 2 runs
  12. DeepSeek Chat — Cognum 51.44, type: Social Engineer, 2 runs
  13. Grok 4.1 Fast (xAI) — Cognum 51.15, type: Social Engineer, 2 runs
  14. gpt-5.5 — Cognum 50.73, type: Social Engineer, 2 runs
  15. DeepSeek V3.2 — Cognum 50.35, type: Social Engineer, 2 runs

The cognitive
leaderboard.

How 40 AI models think, ranked by cognitive profiling rather than capability benchmarks. Cognum (CQ) is the composite score across ten cognitive dimensions, nine labs, 83 environments.

Skip to tableMethodologyProfile your AI

Filters

Section 01 · Filters
··········

Leaderboard

Section 02 · Leaderboard
40 models across all labs
→ Methodology
Top 20 Index
1Claude Sonnet 4
55.20
2Claude Opus 4.6
55.14
3Claude Sonnet 4.6
54.78
4Claude Opus 4.7 (STACK)
53.72
5GPT-5.4
53.25
6mistralai/mistral-large-3-675b-instruct-2512
52.87
7DeepSeek V4 Flash (LM Game Labs, 2x DGX Spark)
52.43
8Claude Haiku 4.5
52.24
9Claude Opus 4.7
51.82
10gemini-2.5-flash
51.71
11x-ai/grok-4.20
51.52
12DeepSeek Chat
51.44
13Grok 4.1 Fast (xAI)
51.15
14gpt-5.5
50.73
15DeepSeek V3.2
50.35
16Mistral Medium 3.1
50.33
17qwen3.5-plus
49.88
18meta/llama-4-maverick-17b-128e-instruct
49.53
19meta-llama/llama-4-maverick
49.31
20qwen/qwq-32b
47.93

Profile your AI

Section 04 · Profile your AI

Want to see your AI model on this leaderboard? Profile it through our API.

View ProtocolGet API Key
KALEI · LM Cognition Lab · Plovdivv1.2 · 40 models