Combined Model Ranking

See which AI models perform best on Combined, which ones stay reliable, and where the biggest gaps appear. Sort by: Metric ↑.

Models Shown

Average Combined Score

0.6

Best Model

Span-02 0.0

Failure Reasons

With failure reason Invalid tool call180 With failure reason Wrong answer128 With failure reason API error62 With failure reason No answer56 With failure reason Timed out11 With failure reason Did not follow instructions1 With failure reason Extra formatting1

451/451

Rank	Model	Company	Combined Score	Score	Total Cost	Tests Correct	Response Time (avg)
#346	KAT Coder AIR V2.5 medium	Kwaipilot	0.7	0.5	$0.048	1/2	19.6s
Total Tests 2 Wrong Tests 1 Total Cost $0.048 Response Time (avg) 19.6s
#356	Inkling Small none	Thinkingmachines	0.7	0.5	$0.054	1/2	9.33s
Total Tests 2 Wrong Tests 1 Total Cost $0.054 Response Time (avg) 9.33s
#360	Ling 2.6 1t default	Inclusionai	0.7	0.5	$0.016	1/2	23.8s
Total Tests 2 Wrong Tests 1 Total Cost $0.016 Response Time (avg) 23.8s
#72	Muse Spark 1.1 low	Meta	0.7	0.9	$0.885	1/2	29.4s
Total Tests 2 Wrong Tests 1 Total Cost $0.885 Response Time (avg) 29.4s
#97	Ling 3.1 Flash medium	Inclusionai	0.7	0.8	$0.000	1/2	306.5s
Total Tests 2 Wrong Tests 1 Total Cost $0.000 Response Time (avg) 306.5s
#182	MiMo-V2.6-Flash low	Xiaomi	0.7	0.7	$0.200	1/2	20.8s
Total Tests 2 Wrong Tests 1 Total Cost $0.200 Response Time (avg) 20.8s
#260	Ling 3.1 Flash low	Inclusionai	0.7	0.6	$0.000	1/2	235.1s
Total Tests 2 Wrong Tests 1 Total Cost $0.000 Response Time (avg) 235.1s
#177	Qwen3.6 27B medium	Qwen	0.7	0.7	$1.021	0/2	584.1s
Total Tests 2 Wrong Tests 2 Total Cost $1.021 Response Time (avg) 584.1s
#223	Mercury 2 medium	Inception	0.7	0.7	$0.121	1/2	7.84s
Total Tests 2 Wrong Tests 1 Total Cost $0.121 Response Time (avg) 7.84s
#244	Kimi K2.5 medium	Moonshot AI	0.7	0.6	$0.841	1/2	89.2s
Total Tests 2 Wrong Tests 1 Total Cost $0.841 Response Time (avg) 89.2s
#114	Qwen3.8 Flash Next low	Qwen	0.7	0.8	~$0.045	1/2	98.9s
Total Tests 2 Wrong Tests 1 Total Cost ~$0.045 Response Time (avg) 98.9s
#119	GPT-5.4 Mini medium	OpenAI	0.7	0.8	$1.102	1/2	59.6s
Total Tests 2 Wrong Tests 1 Total Cost $1.102 Response Time (avg) 59.6s
#122	Qwen3.8 2.4T A95B high	Qwen	0.7	0.8	$2.949	1/2	266.1s
Total Tests 2 Wrong Tests 1 Total Cost $2.949 Response Time (avg) 266.1s
#169	Qwen3.5 Plus 2026-02-15 medium	Qwen	0.7	0.7	$0.567	1/2	175.8s
Total Tests 2 Wrong Tests 1 Total Cost $0.567 Response Time (avg) 175.8s
#173	Qwen3.7 Flash high	Qwen	0.7	0.7	$0.063	1/2	232.0s
Total Tests 2 Wrong Tests 1 Total Cost $0.063 Response Time (avg) 232.0s

Combined Ranking

Filter models

Top Models by Combined Score

Combined Score vs Total Cost

Top Models by Response Time (avg)

Combined Ranking

Filter models

Top Models by Combined Score

Combined Score vs Total CostEstimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 0.4535 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.044834.

Top Models by Response Time (avg)

Combined Score vs Total Cost