Complex Reasoning on Big Bench Extra Hard
74.4Micro Avg ScoreGemma 4 31B
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemma 4 31BModel size=31B, Thinking mode=true2026.07 | 74.4 | |
| Gemma 4 26B-A4BModel size=26B-A4B, Thinking mode=true2026.07 | 64.8 | |
| Gemma 4 12BModel size=12B, Thinking mode=true2026.07 | 53 | |
| Gemma 4 E4BModel size=E4B, Thinking mode=true2026.07 | 33.1 | |
| Gemma 4 E2BModel size=E2B, Thinking mode=true2026.07 | 21.9 | |
| Gemma 3 27BModel size=27B, Thinking mode=false2026.07 | 19.3 |