Combined Model Ranking

See which AI models perform best on Combined, which ones stay reliable, and where the biggest gaps appear. Sort by: Response Time (avg) ↓.

Models Shown

Average Combined Score

5.9

Best Model

Qwen3.6 35B A3B 3.0

Failure Reasons

With failure reason Invalid tool call150 With failure reason Wrong answer99 With failure reason No answer46 With failure reason API error37 With failure reason Timed out9 With failure reason Did not follow instructions1 With failure reason Extra formatting1

330/330

Rank	Model	Company	Combined Score	Score	Total Cost	Tests Correct	Response Time (avg)
#191	Mimo V2 PRO medium	Xiaomi	2.3	6.3	$0.333	0/1	64.7s
Total Tests 1 Wrong Tests 1 Total Cost $0.333 Response Time (avg) 64.7s
#3	GPT-6 Astra max	OpenAI	10.0	9.9	$3.803	2/2	64.0s
Total Tests 2 Wrong Tests 0 Total Cost $3.803 Response Time (avg) 64.0s
#122	GLM 5.3 high	Z.ai	6.4	7.3	$0.403	1/2	64.0s
Total Tests 2 Wrong Tests 1 Total Cost $0.403 Response Time (avg) 64.0s
#72	Inkling high	Thinkingmachines	7.3	8.0	$1.046	1/2	63.8s
Total Tests 2 Wrong Tests 1 Total Cost $1.046 Response Time (avg) 63.8s
#57	Grok 4.6 medium	X AI	10.0	8.4	$1.713	2/2	62.7s
Total Tests 2 Wrong Tests 0 Total Cost $1.713 Response Time (avg) 62.7s
#184	Qwen3.6 Max Preview none	Qwen	6.5	6.4	$0.228	1/2	61.6s
Total Tests 2 Wrong Tests 1 Total Cost $0.228 Response Time (avg) 61.6s
#210	Gemini 2.5 Flash none	Google	3.0	6.0	$0.017	0/2	61.2s
Total Tests 2 Wrong Tests 2 Total Cost $0.017 Response Time (avg) 61.2s
#254	Kimi K2.5 none	Moonshot AI	2.8	5.4	$0.101	0/2	61.0s
Total Tests 2 Wrong Tests 2 Total Cost $0.101 Response Time (avg) 61.0s
#218	Dots 3 Note Preview medium	Dots Studio	9.9	5.9	$0.000	2/2	60.8s
Total Tests 2 Wrong Tests 0 Total Cost $0.000 Response Time (avg) 60.8s
#22	Gemini 3.8 Flash medium	Google	8.7	9.1	$0.653	1/2	60.3s
Total Tests 2 Wrong Tests 1 Total Cost $0.653 Response Time (avg) 60.3s
#110	GPT-5.4 Mini medium	OpenAI	6.9	7.5	$0.786	1/2	59.6s
Total Tests 2 Wrong Tests 1 Total Cost $0.786 Response Time (avg) 59.6s
#90	Seed-2.0-Lite medium	Bytedance Seed	6.4	7.8	$0.236	1/2	58.5s
Total Tests 2 Wrong Tests 1 Total Cost $0.236 Response Time (avg) 58.5s
#59	GPT-5.2 medium	OpenAI	10.0	8.4	$1.182	2/2	58.5s
Total Tests 2 Wrong Tests 0 Total Cost $1.182 Response Time (avg) 58.5s
#6	Gemini 3.7 Flash high	Google	10.0	9.8	$0.646	2/2	57.2s
Total Tests 2 Wrong Tests 0 Total Cost $0.646 Response Time (avg) 57.2s
#251	KAT-Coder-Air V2.5 low	Kwaipilot	6.4	5.4	$0.046	1/2	55.9s
Total Tests 2 Wrong Tests 1 Total Cost $0.046 Response Time (avg) 55.9s

←

1 9 10 11 22

→

Combined Ranking

Filter models

Top Models by Combined Score

Combined Score vs Total Cost

Top Models by Response Time (avg)