File:Big Bench Hard performance vs AI scale.png
Jump to navigation
Jump to search
Size of this preview: 800 × 500 pixels. Other resolutions: 320 × 200 pixels | 640 × 400 pixels | 1,024 × 640 pixels | 1,280 × 800 pixels | 2,400 × 1,500 pixels.
Original file (2,400 × 1,500 pixels, file size: 154 KB, MIME type: image/png)
Summary
| Description |
English: https://epochai.org/blog/how-predictable-is-language-model-benchmark-performance
Figure 2: Aggregate benchmark performance for BIG-Bench Hard and MMLU is fairly predictable from compute scaling. Sigmoid fits are shown in black for both plots, with bold lines showing data used for fitting and dashed lines showing extrapolation. |
| Date | |
| Source | https://epochai.org/blog |
| Author | Epoch AI |
Licensing
This file is licensed under the Creative Commons Attribution 4.0 International license.
- You are free:
- to share – to copy, distribute and transmit the work
- to remix – to adapt the work
- Under the following conditions:
- attribution – You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
File history
Click on a date/time to view the file as it appeared at that time.
| Date/Time | Thumbnail | Dimensions | User | Comment | |
|---|---|---|---|---|---|
| current | 00:10, 25 September 2024 | | 2,400 × 1,500 (154 KB) | wikimediacommons>Cosmia Nebula | Uploaded a work by Epoch AI from https://epochai.org/blog with UploadWizard |
File usage
The following page uses this file:
