Combined Model Ranking

AI BENCHY Category

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

6.3

Best Model

Failure Reasons

With failure reason Wrong answer52 With failure reason Invalid tool call19 With failure reason API error13 With failure reason No answer2 With failure reason Timed out2 With failure reason Did not follow instructions1

Rank	Model	Company	Combined Score	Score	Tests Correct	Response Time (avg)
#114	Qwen3.5 Plus 2026-04-20 none	Qwen	2.8	5.7	0/1	13.3s
#115	Qwen3.5-27B none	Qwen	2.8	5.7	0/1	9.39s
#112	GLM 5.1 none	Z.ai	2.8	5.7	0/1	32.6s
#135	Kimi K2.5 none	Moonshot AI	2.8	5.2	0/1	19.2s
#158	GLM 4.7 Flash medium	Z.ai	2.8	4.4	0/1	65.6s
#16	Gemini 3 Flash Preview low	Google	3.0	8.4	0/1	3.27s
#20	Gemini 3.5 Flash none	Google	3.0	8.1	0/1	0ms
#27	Gemma 4 31B medium	Google	3.0	7.8	0/1	0ms
#32	Gemini 3.5 Flash minimal	Google	3.0	7.7	0/1	3.56s
#34	Qwen3.7 Max none	Qwen	3.0	7.7	0/1	2.17s
#35	Gemini 3 PRO Preview medium	Google	3.0	7.6	0/1	10.4s
#46	Qwen3.6 35B A3B medium	Qwen	3.0	7.4	0/1	0ms
#50	Gemini 3.1 Flash Lite Preview low	Google	3.0	7.4	0/1	11.9s
#58	Gemini 3.1 Flash Lite Preview none	Google	3.0	7.2	0/1	3.20s
#61	Gemini 3.1 Flash Lite low	Google	3.0	7.2	0/1	4.48s

Combined Ranking