Hugging Face's logo

inclusionAI
/
GroveMoE-Inst

Text Generation
Transformers
Safetensors
qwen3_moe
conversational
custom_code
Model card Files Community
1
HaoxingChen commited on
Commit
85f754b
·
verified ·
1 Parent(s): ac52d21

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -25,8 +25,8 @@ We introduce **GroveMoE**, a new sparse architecture using **adjugate experts**
25
 
26
  ## Performance
27
 
28
- | Model | Activated Params | MMLU-Pro | SuperGPQA | GPQA-Diamond | Omni-math | AIME'25 | MultiPL-E | LiveCodeBench v6 |
29
- |:-----:|:----------------:|:------------:|:-------------:|:------------:|:-----------------:|:------------:|:------------------:|:------------------:|
30
  |Llama4-Scout| 17B | 64.9 | 42.0 | 55.6 | 56.6 | 30.2 | 10.0 | 45.0 | 32.0 |
31
  |Qwen3-30B-A3B| 3B | 63.3 | 40.5 | 51.7 | 60.3 | 33.7 | 21.7 | 66.0 | 29.4 |
32
  |Qwen3-32B| 32B | 68.2 | 43.0 | 53.6 | 59.5 | 31.8 | 22.9 | 68.6 | 28.6 |
 
25
 
26
  ## Performance
27
 
28
+ | Model | Activated Params | MMLU-Pro | SuperGPQA | GPQA-Diamond | OlympiadBench | Omni-math | AIME'25 | MultiPL-E | LiveCodeBench v6 |
29
+ |:-----:|:----------------:|:------------:|:-------------:|:------------:|:-----------------:|:------------:|:------------------:|:------------------:|:------------------:|
30
  |Llama4-Scout| 17B | 64.9 | 42.0 | 55.6 | 56.6 | 30.2 | 10.0 | 45.0 | 32.0 |
31
  |Qwen3-30B-A3B| 3B | 63.3 | 40.5 | 51.7 | 60.3 | 33.7 | 21.7 | 66.0 | 29.4 |
32
  |Qwen3-32B| 32B | 68.2 | 43.0 | 53.6 | 59.5 | 31.8 | 22.9 | 68.6 | 28.6 |