Benchmark Performance
| Benchmark | Score | Unit | Evaluated At | Notes | Source |
|---|
| MMLU | 84.5 | % | 2023-12-06 | 5-shot | view |
| HUMANEVAL | 76.4 | pass@1 | 2023-12-06 | — | view |
| GSM8K | 82.4 | % | 2023-12-06 | 0-shot CoT | view |
| MATH | 58.2 | % | 2023-12-06 | 0-shot CoT | view |
| BBH | 79.1 | % | 2023-12-06 | 3-shot CoT | view |
| GPQA | 47.7 | % | 2023-12-06 | 0-shot | view |
| IFEVAL | 75.1 | % | 2023-12-06 | prompt_strict | view |
| ARC | 94.1 | % | 2023-12-06 | challenge | view |
| MUSR | 57.8 | % | 2023-12-06 | 0-shot | view |
| WINOGRANDE | 84.5 | % | 2023-12-06 | 0-shot | view |
Pricing
| Tier | Price | Currency |
|---|
| Input | $0.5 / Mtok | USD |
| Output | $1.5 / Mtok | USD |
| Cache Read | $0 / Mtok | USD |
| Cache Write | $0 / Mtok | USD |
Source:
https://ai.google.dev/pricing
· as of 2023-12-06
Compliance
- Data Residency: US
- SOC2: ✓
- HIPAA: ✗
- GDPR: ✓
- ISO 27001: ✓
Gemini 1.0 Pro
Model Genel Bakışı
Google Gemini 1.0 Pro 首代模型, 32K 上下文, 在 MMLU/GSM8K 上超越 GPT-3.5, 多模态能力初步集成。
Temel Özellikler
| Satıcı | Sürüm | Yayın Tarihi | Bağlam Penceresi | Giriş Modları | Çıkış Modları | Lisans |
|---|
| Google | 1.0-pro | 2023-12-06 | 32K | text | text | Proprietary |
| Benchmark | Puan | Birim | Notlar |
|---|
| MMLU (Massive Multitask Language Understanding) | 84.5 | % | 5-shot |
| HumanEval | 76.4 | pass@1 | — |
| GSM8K (Grade School Math 8K) | 82.4 | % | 0-shot CoT |
| MATH | 58.2 | % | 0-shot CoT |
| BBH (BIG-Bench Hard) | 79.1 | % | 3-shot CoT |
| GPQA | 47.7 | % | 0-shot |
| IFEval | 75.1 | % | prompt_strict |
| ARC | 94.1 | % | challenge |
| MUSR | 57.8 | % | 0-shot |
| WinoGrande | 84.5 | % | 0-shot |
Fiyatlandırma
| Giriş | Çıkış | Önbellek Okuma | Önbellek Yazma |
|---|
| — | — | — | — |
milyon token başına
Güçlü Yönler
- MMLU score 84.5, strong knowledge reasoning.
Zayıf Yönler
Kullanım Senaryoları
Referanslar