Z AIのモデル：知能・性能・料金
Artificial AnalysisはZ AIの23個のモデルをベンチマークしています。以下では、これらのモデルの主要指標を比較します。
- 知能が最も高いZ AIのモデルはGLM-5.3 (Max)（32）です。
- 速度では、タスクあたりの時間が最も短いモデルはGLM-5.3 (Low)（18.1分）です。
- 最初の回答トークンまでの時間が最も短いモデルはGLM-5.3 (Low)（14.12秒）です。
- タスクあたりの費用が最も低いモデルはGLM-5.3-Flash（$0.58）です。モデル間の料金差は最大8.6倍です。
知能
Artificial Analysis Intelligence Index
Intelligence Index とタスクあたりのコスト
費用
Intelligence Index タスクあたりのコスト
速度と遅延
Intelligence Indexのタスクあたりの時間
能力スコア
能力指数
Incorporates 5 evaluations: AA-Briefcase v1.1, AA-Omniscience v1.1, HLE-Diamond, AutomationBench-AA, GDP.pdf · Higher is better
Incorporates 4 evaluations: AutomationBench-AA, AA-Briefcase v1.1, AA-Omniscience v1.1, GDP.pdf · Higher is better
Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, MLCR-AA, AutomationBench-AA, HLE-Diamond · Higher is better
Incorporates 7 evaluations: AA-Omniscience v1.1, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1, HLE-Diamond, Terminal-Bench 4.0, FrontierCode 2.0, AA-Briefcase v1.1 · Higher is better
Incorporates 4 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf · Higher is better
Z AIのすべてのリリース
詳細
ウェイト | プロバイダーのベンチマーク | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| GLM-5.3 (Max) |  Z AI | 32 | 753B 推論時に40Bが有効 | 1M | $0.9 | 31.5 | 63 |   +21 | ||
| GLM-5.3-Flash | Z AI | 28 | 320B 推論時に18Bが有効 | 1M | $0.1 | 39.4 | 57 |  +19 | ||
| GLM-5.3 (Low) | Z AI | 23 | 753B 推論時に40Bが有効 | 1M | $0.9 | 18.1 | 48 |   +5 | ||
| GLM-4.5V (Non-reasoning) | Z AI | - | 108B 推論時に12Bが有効 | 64k | $0.4 | - | 57 |  | ||
| GLM-5-Turbo | Z AI | - | - | 200k | - | - | - | 利用不可 | - | |
| GLM-4.5 (Reasoning) | Z AI | - | 355B 推論時に32Bが有効 | 128k | - | - | - | - | ||
| GLM 5V Turbo (Reasoning) | Z AI | - | - | 200k | - | - | - | 利用不可 | - | |
| GLM-4.7-Flash (Reasoning) | Z AI | - | 31.2B 推論時に3Bが有効 | 200k | $0.1 | - | 116 |   | ||
| GLM-4.5V (Reasoning) | Z AI | - | 108B 推論時に12Bが有効 | 64k | $0.4 | - | 53 | | ||
| GLM-5 (Reasoning) | Z AI | - | 744B 推論時に40Bが有効 | 200k | $0.7 | - | 64 |   +2 | ||
| GLM-4.6V (Non-reasoning) | Z AI | - | 108B 推論時に12Bが有効 | 128k | $0.3 | - | 33 | | ||
| GLM-5.1 (Reasoning) | Z AI | - | 744B 推論時に40Bが有効 | 200k | $0.8 | - | 77 |  +2 | ||
| GLM-4.5-Air | Z AI | - | 106B 推論時に12Bが有効 | 128k | $0.3 | - | 66 | | ||
| GLM-4.6 (Reasoning) | Z AI | - | 357B 推論時に32Bが有効 | 200k | $0.4 | - | 29 | | ||
| GLM-4.7 (Reasoning) | Z AI | - | 357B 推論時に32Bが有効 | 200k | $0.5 | - | 34 | | ||
| GLM-4.7 (Non-reasoning) | Z AI | - | 357B 推論時に32Bが有効 | 200k | $0.5 | - | 31 | | ||
| GLM-5.1 (Non-reasoning) | Z AI | - | 744B 推論時に40Bが有効 | 200k | $0.8 | - | 62 |  | ||
| GLM-4.6 (Non-reasoning) | Z AI | - | 357B 推論時に32Bが有効 | 200k | $0.6 | - | 32 | | ||
| GLM-4.7-Flash (Non-reasoning) | Z AI | - | 31.2B 推論時に3Bが有効 | 200k | $0.1 | - | 78 | | ||
| GLM-4.6V (Reasoning) | Z AI | - | 108B 推論時に12Bが有効 | 128k | $0.3 | - | 39 | | ||
| GLM-5.2 (Non-reasoning) | Z AI | - | 753B 推論時に40Bが有効 | 1M | $0.9 | - | 169 |   +3 | ||
| GLM-5 (Non-reasoning) | Z AI | - | 744B 推論時に40Bが有効 | 200k | $0.7 | - | 51 | | ||
| GLM-5.2 (Max) | Z AI | - | 753B 推論時に40Bが有効 | 1M | $0.9 | - | 90 | +14 |