General Knowledge on AGIEval En
78.73CoT EMNemotron-3-Ultra 550B-A55B-Base
Evaluation results
| Method | Links | |
|---|---|---|
| Nemotron-3-Ultra 550B-A55B-Baseshots=3/5-shot, reasoning=Chain-of-thought (CoT)2026.06 | 78.73 | |
| N-3-Super 120B-A12B-BaseShots=3/5, Chain-of-Thought (CoT)=true2026.04 | 77.92 | |
| Kimi-K2 Baseshots=3/5-shot, reasoning=Chain-of-thought (CoT)2026.06 | 72.55 | |
| DeepSeek-V3.2 Exp-Baseshots=3/5-shot, reasoning=Chain-of-thought (CoT)2026.06 | 70.13 | |
| GLM-4.5 Baseshots=3/5-shot, reasoning=Chain-of-thought (CoT)2026.06 | 70.06 | |
| Mistral-Large-3 675B-Base-2512shots=3/5-shot, reasoning=Chain-of-thought (CoT)2026.06 | 69.3 | |
| GLM-4.5 Air-BaseShots=3/5, Chain-of-Thought (CoT)=true2026.04 | 62.4 | |
| Ling-flash base-2.0Shots=3/5, Chain-of-Thought (CoT)=true2026.04 | 61.7 |