AI BENCHY Compare

Qwen: Qwen3.5-122B-A10B vs Z.ai: GLM 4.7 Flash

Last updated at: 2026-04-14

Metric	Qwen3.5-122B-A10B Qwen3.5-122B-A10B none Release: 2026-02-24	GLM 4.7 Flash GLM 4.7 Flash medium Release: 2026-01-19

Metric	Qwen3.5-122B-A10B Qwen3.5-122B-A10B none Release: 2026-02-24	GLM 4.7 Flash GLM 4.7 Flash medium Release: 2026-01-19
Score	5.7	4.6
Rank	#66	#89
Consistency	9.2	6.3
Tests Correct
Attempt pass rate	38.9%	38.9%
Flaky tests	2	8
Total Runs	54	54
Cost per result	0.360	1.126
Total Cost	$0.022	$0.046
Input Price	$0.260 / 1M	$0.060 / 1M
Output Price	$2.080 / 1M	$0.400 / 1M
Output Tokens	3,341	39,688
Reasoning Tokens	0	72,401
Response Time (avg)	3.69s	32.33s
Response Time (max)	46.00s	174.55s
Response Time (total)	66.50s	355.65s

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Category Breakdown

Anti-AI Tricks	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Output Tokens	Reasoning Tokens
Qwen3.5-122B-A10B	4.8	10.0	25.0%	0		1.59s	312	0
GLM 4.7 Flash	4.7	5.9	41.7%	2		14.95s	1,122	6,110

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Output Tokens	Reasoning Tokens
Qwen3.5-122B-A10B	4.3	1.1	66.7%	1		3.44s	659	0
GLM 4.7 Flash	3.6	2.1	33.3%	1		21.26s	969	6,936

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Output Tokens	Reasoning Tokens
Qwen3.5-122B-A10B	3.0	10.0	0.0%	0		46.00s	1,137	0
GLM 4.7 Flash	2.8	2.1	33.3%	1		65.57s	2,585	20,648

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Output Tokens	Reasoning Tokens
Qwen3.5-122B-A10B	10.0	10.0	100.0%	0		1.01s	243	0
GLM 4.7 Flash	6.3	10.0	50.0%	0		1.51s	584	2,755

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Output Tokens	Reasoning Tokens
Qwen3.5-122B-A10B	5.3	10.0	33.3%	0		465ms	15	0
GLM 4.7 Flash	3.5	4.4	33.3%	2		174.55s	33,000	25,394

General Intelligence	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Output Tokens	Reasoning Tokens
Qwen3.5-122B-A10B	5.0	10.0	0.0%	0		1.12s	66	0
GLM 4.7 Flash	3.6	9.7	0.0%	0		18.14s	18	2,138

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Output Tokens	Reasoning Tokens
Qwen3.5-122B-A10B	4.5	6.8	16.7%	1		585ms	70	0
GLM 4.7 Flash	6.2	5.8	66.7%	1		2.97s	388	2,181

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Output Tokens	Reasoning Tokens
Qwen3.5-122B-A10B	5.4	10.0	33.3%	0		982ms	575	0
GLM 4.7 Flash	2.9	7.2	11.1%	1		12.90s	798	5,225

Tool Calling	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Output Tokens	Reasoning Tokens
Qwen3.5-122B-A10B	10.0	10.0	100.0%	0		2.04s	264	0
GLM 4.7 Flash	10.0	10.0	100.0%	0		15.95s	224	1,014

Quick Compare

Switch Comparison Pair

MiniMax M2.5mediumFree AvailablevsQwen3.5-122B-A10Bnone MiMo-V2-FlashnonevsGLM 4.7 Flashmedium Grok 4.1 FastnonevsGLM 4.7 Flashmedium Mistral Small 4mediumvsQwen3.5-122B-A10Bnone gpt-oss-120bmediumFree AvailablevsQwen3.5-122B-A10Bnone GPT-5.4 NanononevsGLM 4.7 Flashmedium Mercury 2nonevsGLM 4.7 Flashmedium Qwen3.5-9BnonevsGLM 4.7 Flashmedium GPT-4o-mininonevsGLM 4.7 Flashmedium MiniMax M2.7mediumvsQwen3.5-122B-A10Bnone ElephantmediumvsQwen3.5-122B-A10Bnone Nemotron 3 SupernoneFree AvailablevsGLM 4.7 Flashmedium