ChibuUkachi commited on
Commit
79613cc
·
verified ·
1 Parent(s): de781a1

update results

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -205,12 +205,12 @@ The model was evaluated on the ifeval, mmlu_pro and gsm8k_platinum using [lm-ev
205
 
206
  ### Accuracy
207
 
208
-
209
  | Benchmark | inference-optimization/MiniMax-M2.5-BF16 | inference-optimization/MiniMax-M2.5.w8a8 | Recovery (%) |
210
- |-----------|------------------------------------------|-------------------------------------------|--------------|
211
- | GSM8k Platinum (0-shot) | 95.15 | 96.36 | 101.27 |
212
- | IfEval (0-shot) | 88.17 | 85.58 | 97.06 |
213
- | AIME 2025 | 87.50 | 84.17 | 96.19 |
214
  | GPQA diamond | 83.67 | 84.51 | 101.01 |
215
- | Math 500 | 87.33 | 87.60 | 100.31 |
216
- | Mmlu Pro Chat | 80.83 | 81.25 | 100.51 |
 
 
205
 
206
  ### Accuracy
207
 
 
208
  | Benchmark | inference-optimization/MiniMax-M2.5-BF16 | inference-optimization/MiniMax-M2.5.w8a8 | Recovery (%) |
209
+ |-----------|------------------------------------------|------------------------------------------|--------------|
210
+ | GSM8k Platinum (0-shot) | 95.15 | 95.18 | 100.03 |
211
+ | IfEval (0-shot) | 92.05 | 90.33 | 98.13 |
212
+ | AIME 2025 | 87.50 | 88.33 | 100.95 |
213
  | GPQA diamond | 83.67 | 84.51 | 101.01 |
214
+ | Math 500 | 87.33 | 87.13 | 99.77 |
215
+ | MMLU Pro Chat | 80.83 | 81.25 | 100.51 |
216
+