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)
#41	Muse Wonder low	Meta	1.0	0.9	$2.637	2/2	24.7s
Total Tests 2 Wrong Tests 0 Total Cost $2.637 Response Time (avg) 24.7s
#43	Seed 2.1 Turbo high	Bytedance Seed	1.0	0.9	$1.892	2/2	408.8s
Total Tests 2 Wrong Tests 0 Total Cost $1.892 Response Time (avg) 408.8s
#44	Muse Wonder minimal	Meta	1.0	0.9	$1.639	2/2	16.1s
Total Tests 2 Wrong Tests 0 Total Cost $1.639 Response Time (avg) 16.1s
#45	Muse Spark Open xhigh	Meta	1.0	0.9	$2.081	2/2	134.0s
Total Tests 2 Wrong Tests 0 Total Cost $2.081 Response Time (avg) 134.0s
#47	Qwen3.8 Max (0902) medium	Qwen	1.0	0.9	$1.096	2/2	94.4s
Total Tests 2 Wrong Tests 0 Total Cost $1.096 Response Time (avg) 94.4s
#51	Claude Opus 5 low	Anthropic	1.0	0.9	$2.350	2/2	21.1s
Total Tests 2 Wrong Tests 0 Total Cost $2.350 Response Time (avg) 21.1s
#60	Qwen3.8 MAX low	Qwen	1.0	0.9	$1.089	2/2	98.2s
Total Tests 2 Wrong Tests 0 Total Cost $1.089 Response Time (avg) 98.2s
#61	GPT-5.4 medium	OpenAI	1.0	0.9	$2.213	2/2	29.8s
Total Tests 2 Wrong Tests 0 Total Cost $2.213 Response Time (avg) 29.8s
#62	Muse Spark Open medium	Meta	1.0	0.9	$1.260	2/2	72.2s
Total Tests 2 Wrong Tests 0 Total Cost $1.260 Response Time (avg) 72.2s
#63	DeepSeek V4.1 Flash high	DeepSeek	1.0	0.9	$0.617	2/2	27.6s
Total Tests 2 Wrong Tests 0 Total Cost $0.617 Response Time (avg) 27.6s
#64	DeepSeek V4.1 Flash medium	DeepSeek	1.0	0.9	$0.591	2/2	22.2s
Total Tests 2 Wrong Tests 0 Total Cost $0.591 Response Time (avg) 22.2s
#66	GPT-5.2 medium	OpenAI	1.0	0.9	$1.558	2/2	58.5s
Total Tests 2 Wrong Tests 0 Total Cost $1.558 Response Time (avg) 58.5s
#67	Qwen3.8 27B high	Qwen	1.0	0.9	~$0.298	2/2	185.6s
Total Tests 2 Wrong Tests 0 Total Cost ~$0.298 Response Time (avg) 185.6s
#68	MiMo-V2.6-Pro medium	Xiaomi	1.0	0.9	$0.586	2/2	50.8s
Total Tests 2 Wrong Tests 0 Total Cost $0.586 Response Time (avg) 50.8s
#69	Seed 2.1 Turbo medium	Bytedance Seed	1.0	0.9	$2.042	2/2	400.3s
Total Tests 2 Wrong Tests 0 Total Cost $2.042 Response Time (avg) 400.3s

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: 3.0102 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.297613.

Top Models by Response Time (avg)

Combined Score vs Total Cost