modelgrep

Mistral: Mistral Large 3 2512 vs Z.ai: GLM 4.6V

Z.ai: GLM 4.6V wins on more metrics (5 of 9), but the right pick depends on what you optimize for — see the breakdown below.

MetricMistral: Mistral Large 3 2512Z.ai: GLM 4.6V
Intelligence Index22.823.4
Coding Index22.719.7
GPQA Diamond68%72%
Design Arena Elo1206
Speed (tokens/sec)3060
Latency787ms1.5s
Input price /M$0.500$0.300
Output price /M$1.50$0.900
Context window262K131K
CapabilitiesToolsJSONVisionReasoningToolsJSONVision