Key Specifications
| Vendor | google |
| Version | 1.5-flash-8b |
| Release Date | 2024-10-03 |
| Context Window | 1e+06 tokens |
| Input Modalities | text, image, audio, video |
| Output Modalities | text |
| License | Proprietary |
| Documentation | https://ai.google.dev/gemini-api/docs |
Benchmark Performance
| Benchmark |
Score |
Unit |
Evaluated At |
Notes |
Source |
| MMLU |
76.6 |
% |
2024-10-03 |
5-shot |
view |
| HUMANEVAL |
70.7 |
pass@1 |
2024-10-03 |
— |
view |
| GSM8K |
83.5 |
% |
2024-10-03 |
0-shot CoT |
view |
| MATH |
35 |
% |
2024-10-03 |
0-shot CoT |
view |
| BBH |
74.8 |
% |
2024-10-03 |
3-shot CoT |
view |
| GPQA |
35 |
% |
2024-10-03 |
0-shot |
view |
| IFEVAL |
68.1 |
% |
2024-10-03 |
prompt_strict |
view |
| ARC |
94.5 |
% |
2024-10-03 |
challenge |
view |
| MUSR |
45.6 |
% |
2024-10-03 |
0-shot |
view |
| WINOGRANDE |
79.7 |
% |
2024-10-03 |
0-shot |
view |
Pricing
| Tier |
Price |
Currency |
| Input | $0.0375 / Mtok | USD |
| Output | $0.15 / Mtok | USD |
| Cache Read | $0 / Mtok | USD |
| Cache Write | $0 / Mtok | USD |
Source:
https://ai.google.dev/pricing
· as of 2024-10-03
Compliance
- Data Residency: US
- SOC2: ✓
- HIPAA: ✗
- GDPR: ✓
- ISO 27001: ✓
Gemini 1.5 Flash-8B
Model Overview
Google Gemini 1.5 Flash-8B 8B 参数经济型, 1M 上下文, 更低延迟, 适合高频实时多模态任务。
Core Specifications
| Vendor |
Version |
Release Date |
Context Window |
Input Modalities |
Output Modalities |
License |
| Google |
1.5-flash-8b |
2024-10-03 |
1000K |
text, image, audio, video |
text |
Proprietary |
| Benchmark |
Score |
Unit |
Notes |
| MMLU (Massive Multitask Language Understanding) |
76.6 |
% |
5-shot |
| HumanEval |
70.7 |
pass@1 |
— |
| GSM8K (Grade School Math 8K) |
83.5 |
% |
0-shot CoT |
| MATH |
35.0 |
% |
0-shot CoT |
| BBH (BIG-Bench Hard) |
74.8 |
% |
3-shot CoT |
| GPQA |
35.0 |
% |
0-shot |
| IFEval |
68.1 |
% |
prompt_strict |
| ARC |
94.5 |
% |
challenge |
| MUSR |
45.6 |
% |
0-shot |
| WinoGrande |
79.7 |
% |
0-shot |
Pricing
| Input |
Output |
Cache Read |
Cache Write |
| — |
— |
— |
— |
per million tokens
Strengths
- Input Modalities: text, image, audio.
Weaknesses
- Proprietary, not self-hostable.
Use Cases
- Code generation and debugging
- Vision and image understanding
References