Long Context Reasoning on RULER 1M
91.64AccuracyNemotron 3 Super
Evaluation Results
| Method | Links | |
|---|---|---|
| Nemotron 3 Super2026.04 | 91.64 | |
| Qwen3.5-122B-A10B2026.04 | 91.33 | |
| GPT-OSS-120B2026.04 | 22.3 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| Nemotron 3 Super2026.04 | 91.64 | |
| Qwen3.5-122B-A10B2026.04 | 91.33 | |
| GPT-OSS-120B2026.04 | 22.3 |