germanjke commited on
Commit
2ff3e54
·
verified ·
1 Parent(s): c7404fc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -1
README.md CHANGED
@@ -26,7 +26,13 @@ Preference Tuning:
26
 
27
  ## 📊 Benchmarks
28
 
29
- tba
 
 
 
 
 
 
30
 
31
  ## Switching Between Thinking and Non‑Thinking Modes
32
 
 
26
 
27
  ## 📊 Benchmarks
28
 
29
+ | Model | MERA | ruMMLU | Ru Arena Hard | ru AIME 2025 | ru LCB |
30
+ |------------------------------------|:----:|:------:|:-------------:|:------------:|:------:|
31
+ | **T-pro 2.0** | **0.660** | **0.790** | **0.876** | **0.646** | **0.563** |
32
+ | Qwen 3 32B | 0.584 | 0.740 | 0.836 | 0.625 | 0.537 |
33
+ | Ruadapt 3 32B V2 | 0.574 | 0.737 | 0.660 | 0.450 | 0.500 |
34
+ | DeepSeek-R1-Distill-Qwen-32B | 0.508 | 0.702 | 0.426 | 0.402 | 0.493 |
35
+ | Gemma 3 27B | 0.577 | 0.695 | 0.759 | 0.231 | 0.261 |
36
 
37
  ## Switching Between Thinking and Non‑Thinking Modes
38