update images
This commit is contained in:
parent
ef7dff9fd4
commit
f475e4e407
@ -1305,7 +1305,6 @@ scores:
|
|||||||
| 7 | E | 22 | 23 | 15 | 14 | 74 |
|
| 7 | E | 22 | 23 | 15 | 14 | 74 |
|
||||||
| 8 | G | 10 | 12 | 10 | 10 | 42 |
|
| 8 | G | 10 | 12 | 10 | 10 | 42 |
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
### 👉 Subjective Effect Summary
|
### 👉 Subjective Effect Summary
|
||||||
|
|
||||||
@ -1318,6 +1317,8 @@ My personal evaluation aligns with DeepSeek-R1's results,and:
|
|||||||
* Repeating the timeless Scaling Law: The larger the parameters and the more training data, the stronger the model's
|
* Repeating the timeless Scaling Law: The larger the parameters and the more training data, the stronger the model's
|
||||||
performance.
|
performance.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
## Ⅲ Objective Benchmark
|
## Ⅲ Objective Benchmark
|
||||||
|
|
||||||
Now, onto the much-anticipated benchmark testing phase. We won’t bother comparing with models like Qwen or GLM-level
|
Now, onto the much-anticipated benchmark testing phase. We won’t bother comparing with models like Qwen or GLM-level
|
||||||
|
Binary file not shown.
Before Width: | Height: | Size: 6.0 MiB After Width: | Height: | Size: 3.8 MiB |
Loading…
x
Reference in New Issue
Block a user