modelgrep

Qwen: Qwen3 30B A3B Thinking 2507 vs Z.ai: GLM 4.6V

QQwen: Qwen3 30B A3B Thinking 2507qwen/qwen3-30b-a3b-thinking-2507VSZZ.ai: GLM 4.6Vz-ai/glm-4.6v

Qwen: Qwen3 30B A3B Thinking 2507 wins on more metrics (5 of 8), but the right pick depends on what you optimize for — see the breakdown below.

MetricQwen: Qwen3 30B A3B Thinking 2507Z.ai: GLM 4.6V
Intelligence Index22.423.4✓
Coding Index14.619.7✓
GPQA Diamond71%72%✓
Design Arena Elo975✓—
Speed (tokens/sec)98✓60
Latency560ms✓1.5s
Input price /M$0.080✓$0.300
Output price /M$0.400✓$0.900
Context window131K131K
CapabilitiesReasoningToolsJSONReasoningToolsJSONVision
Qwen: Qwen3 30B A3B Thinking 2507 details →Z.ai: GLM 4.6V details →