Benchmark Performance
| Benchmark | Score | Unit | Evaluated At | Notes | Source |
|---|
| MMLU | 68.4 | % | 2023-05-10 | 5-shot | view |
| HUMANEVAL | 44.8 | pass@1 | 2023-05-10 | — | view |
| GSM8K | 49 | % | 2023-05-10 | 0-shot CoT | view |
| MATH | 29.9 | % | 2023-05-10 | 0-shot CoT | view |
| BBH | 52.9 | % | 2023-05-10 | 3-shot CoT | view |
| GPQA | 20.3 | % | 2023-05-10 | 0-shot | view |
| IFEVAL | 44.7 | % | 2023-05-10 | prompt_strict | view |
| ARC | 89.2 | % | 2023-05-10 | challenge | view |
| MUSR | 29.3 | % | 2023-05-10 | 0-shot | view |
| WINOGRANDE | 68.6 | % | 2023-05-10 | 0-shot | view |
Pricing
| Tier | Price | Currency |
|---|
| Input | $1 / Mtok | USD |
| Output | $2 / Mtok | USD |
| Cache Read | $0 / Mtok | USD |
| Cache Write | $0 / Mtok | USD |
Source:
https://ai.google.dev/pricing
· as of 2023-05-10
Compliance
- Data Residency: US
- SOC2: ✓
- HIPAA: ✗
- GDPR: ✓
- ISO 27001: ✓
PaLM 2
Panoramica del modello
Google PaLM 2 大型语言模型, 8K 上下文, 改进多语言/推理/编码能力, Bard 初始版本所用模型。
Specifiche principali
| Fornitore | Versione | Data di rilascio | Finestra di contesto | Modalità di input | Modalità di output | Licenza |
|---|
| Google | palm-2 | 2023-05-10 | 8K | text | text | Proprietary |
Prestazioni benchmark
| Benchmark | Punteggio | Unità | Note |
|---|
| MMLU (Massive Multitask Language Understanding) | 68.4 | % | 5-shot |
| HumanEval | 44.8 | pass@1 | — |
| GSM8K (Grade School Math 8K) | 49.0 | % | 0-shot CoT |
| MATH | 29.9 | % | 0-shot CoT |
| BBH (BIG-Bench Hard) | 52.9 | % | 3-shot CoT |
| GPQA | 20.3 | % | 0-shot |
| IFEval | 44.7 | % | prompt_strict |
| ARC | 89.2 | % | challenge |
| MUSR | 29.3 | % | 0-shot |
| WinoGrande | 68.6 | % | 0-shot |
Prezzi
| Input | Output | Lettura cache | Scrittura cache |
|---|
| — | — | — | — |
per milione di token
Punti di forza
Punti deboli
- HumanEval 44.8，代码能力较弱。
- 闭源专有模型，不支持自托管。
- 上下文窗口 8K 偏小。
Casi d’uso
Riferimenti