unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| RULER | long-context | 94.7 | RULER (1M) | medium | | RULER (1M) | 94.7 | -- | -- | -- | 90.1 | 94.2 | 87.7 | |
| LiveCodeBench | coding | 89.0 | LiveCodeBench (v6) | medium | | LiveCodeBench (v6) | 89.0 | 77.2 | 85.7 | 90.2 | 79.3 | 92.5 | 90.9 | |
| GPQA | reasoning | 87.0 | GPQA (no tools) | medium | | GPQA (no tools) | 87.0 | 86.6 | 86.1 | 91.0 | 87.1 | 87.8 | 88.5 | |
| MMLU-Pro | knowledge | 86.8 | MMLU-Pro | medium | | MMLU-Pro | 86.8 | 81.9 | 85.9 | 88.1 | 88.3 | 87.5 | 86.4 | |
| MMLU-Pro | knowledge | 83.0 | MMLU-ProX (avg en/de/fr/es/it/ja/zh/hi/pt/ko) | medium | | MMLU-ProX (avg en/de/fr/es/it/ja/zh/hi/pt/ko) | 83.0 | 78.4 | 85.8 | 85.0 | 86.4 | 85.6 | 84.3 | |
| IFBench | instruction-following | 81.7 | IFBench (prompt loose) | medium | | IFBench (prompt loose) | 81.7 | 74.6 | 76.6 | 73.7 | 78.2 | 79.1 | 82.0 | |
| SWE-bench Verified | swe | 71.9 | SWE-Bench Verified | medium | | SWE-Bench Verified | 71.9 | 72.2 | 73.8 | 69.5 | 69.9 | 74.0 | 72.4 | |
| LongBench | long-context | 61.9 | Longbench v2 (≤ 1M) | medium | | Longbench v2 (≤ 1M) | 61.9 | -- | -- | -- | 68.9 | 62.1 | 57.0 | |
| Terminal-Bench 2.1 | agentic-coding | 56.4 | Terminal Bench 2.1 | medium | | Terminal Bench 2.1 | 56.4 | 55.5 | 59.3 | 67.2 | 49.9 | 49.2 | 54.2 | |
| SciCode | coding | 44.6 | SciCode (subtask) | medium | | SciCode (subtask) | 44.6 | 38.3 | 47.7 | 52.0 | 48.0 | 50.5 | 48.2 | |
| BrowseComp | agentic | 44.4 | BrowseComp | medium | | BrowseComp | 44.4 | 54.1 | 59.4 | 61.3 | 40.5 | 59.4 | 46.9 | |
| Humanity's Last Exam | knowledge | 37.4 | HLE (with tools) | medium | | HLE (with tools) | 37.4 | -- | 50.4 | 54.0 | 48.3 | 48.2 | 45.1 | |
| Humanity's Last Exam | knowledge | 26.7 | HLE (no tools) | medium | | HLE (no tools) | 26.7 | 23.1 | 27.2 | 34.8 | 28.5 | 37.7 | 32.2 | |
| Terminal-Bench | agentic-coding | 2.1 | medium | Terminal Bench 2.1 |
none scraped.