Evaluation sources/LiveCodeBench
ObservingCoding
LiveCodeBench
LiveCodeBench · Public model evaluation results from LiveCodeBench.
Model results from this source
| Fugu Ultra | 93.2 | 93.2 | 2026-08-05 |
| Fugu | 92.9 | 92.9 | 2026-08-05 |
| Nemotron 3 Ultra 550B A55B | 89 | 89.0 | 2026-06-04 |