General Intelligence Model Ranking

See which AI models perform best on General Intelligence, which ones stay reliable, and where the biggest gaps appear. Sort by: Tests Correct ↑.

Models Shown

Average General Intelligence Score

6.3

Best Model

Qwen3.8 Max (0902) 6.1

Failure Reasons

With failure reason Did not follow instructions116 With failure reason Wrong answer91 With failure reason API error14 With failure reason Timed out4

319/319

Rank	Model	Company	General Intelligence Score	Score	Total Cost	Tests Correct	Response Time (avg)
#58	Inkling Small high	Thinkingmachines	5.3	8.4	$0.398	0/1	3.62s
Total Tests 1 Wrong Tests 1 Total Cost $0.398 Response Time (avg) 3.62s
#61	Gemini 2.5 Flash medium	Google	4.8	8.2	$0.644	0/1	4.86s
Total Tests 1 Wrong Tests 1 Total Cost $0.644 Response Time (avg) 4.86s
#63	Claude Sonnet 5 medium	Anthropic	4.8	8.2	$0.922	0/1	4.32s
Total Tests 1 Wrong Tests 1 Total Cost $0.922 Response Time (avg) 4.32s
#64	Qwen3.8 2.4T A95B low	Qwen	6.1	8.1	$2.672	0/1	23.0s
Total Tests 1 Wrong Tests 1 Total Cost $2.672 Response Time (avg) 23.0s
#65	GPT-5 Mini medium	OpenAI	4.5	8.1	$0.241	0/1	13.5s
Total Tests 1 Wrong Tests 1 Total Cost $0.241 Response Time (avg) 13.5s
#66	Muse Glimmer 30B xhigh	Meta	5.5	8.1	$0.471	0/1	7.41s
Total Tests 1 Wrong Tests 1 Total Cost $0.471 Response Time (avg) 7.41s
#69	DeepSeek V4 Flash 0731 low	DeepSeek	6.5	8.0	$0.072	0/1	7.63s
Total Tests 1 Wrong Tests 1 Total Cost $0.072 Response Time (avg) 7.63s
#73	GPT-5.6 Terra high	OpenAI	5.1	8.0	$0.836	0/1	3.03s
Total Tests 1 Wrong Tests 1 Total Cost $0.836 Response Time (avg) 3.03s
#75	GPT-5.2 Chat none	OpenAI	4.4	7.9	$0.594	0/1	3.20s
Total Tests 1 Wrong Tests 1 Total Cost $0.594 Response Time (avg) 3.20s
#76	Step 3.7 Flash medium	Stepfun	4.0	7.9	$0.495	0/1	6.85s
Total Tests 1 Wrong Tests 1 Total Cost $0.495 Response Time (avg) 6.85s
#77	Qwen3.8 27B low	Qwen	5.0	7.9	~$0.071	0/1	5.37s
Total Tests 1 Wrong Tests 1 Total Cost ~$0.071 Response Time (avg) 5.37s
#79	Qwen3.6 Plus medium	Qwen	5.1	7.8	$0.418	0/1	27.1s
Total Tests 1 Wrong Tests 1 Total Cost $0.418 Response Time (avg) 27.1s
#80	Gemini 3.5 Flash Lite medium	Google	4.7	7.8	$0.272	0/1	2.97s
Total Tests 1 Wrong Tests 1 Total Cost $0.272 Response Time (avg) 2.97s
#82	GPT-5.6 Terra medium	OpenAI	5.5	7.8	$0.523	0/1	2.37s
Total Tests 1 Wrong Tests 1 Total Cost $0.523 Response Time (avg) 2.37s
#84	Qwen3.8 27B medium	Qwen	5.0	7.8	~$0.058	0/1	9.20s
Total Tests 1 Wrong Tests 1 Total Cost ~$0.058 Response Time (avg) 9.20s

General Intelligence Ranking

Filter models

Top Models by General Intelligence Score

General Intelligence Score vs Total Cost

Top Models by Response Time (avg)

General Intelligence Ranking

Filter models

Top Models by General Intelligence Score

General Intelligence Score vs Total CostEstimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 0.7171 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.070898.

Top Models by Response Time (avg)

General Intelligence Score vs Total Cost