Reasoning on AIME 26
88.59ScoreNemotron-3-Super 120B-A12B
Evaluation Results
| Method | Links | |
|---|---|---|
| Nemotron-3-Super 120B-A12BEvaluation Setting=non-reasoning2026.06 | 88.59 | |
| Ling-2.6-1T2026.06 | 87.4 | |
| Ling-2.6-flash2026.06 | 73.85 | |
| GPT-5.4Reasoning Mode=non-reasoning2026.06 | 72.92 | |
| Kimi-K2.5Mode=Instant2026.06 | 66.98 | |
| DeepSeek-V3.2Thinking Mode=nothink2026.06 | 66.41 | |
| GPT-OSS-120BEvaluation Setting=low2026.06 | 60.1 | |
| GLM-5Thinking Mode=non-thinking2026.06 | 49.22 | |
| GPT-5.4-miniEvaluation Setting=non-reasoning2026.06 | 35.68 |