NVIDIA · model
Nemotron 3.5 Lightning 30B A3B NVFP4 benchmark scores
As of 2026-11-22, Nemotron 3.5 Lightning 30B A3B NVFP4 (NVIDIA) has measured scores on 22 benchmarks and estimated scores on 77 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 74.3% | measured |
| AA-HLE | 10.6% | measured |
| AA-SciCode | 32.1% | measured |
| Artificial Analysis Intelligence Index | 5.5% | measured |
| CritPt | 0.0% | measured |
| GDPval-AA | 6.9% | measured |
| GPQA Diamond | 75.6% | measured |
| HLE | 15.5% | estimated ± 6.5 pp, medium confidence |
| IFBench | 72.9% | measured |
| AA-LCR | 49.2% | measured |
| LiveCodeBench v6 | 70.6% | estimated ± 4.4 pp, high confidence |
| AA-Omniscience Accuracy | 14.7% | measured |
| SciCode | 31.4% | measured |
| Terminal-Bench 2.1 | 23.5% | measured |
| BrowseComp | 36.8% | measured |
| HLE w/ tools | 37.1% | estimated ± 5.3 pp, low confidence |
| IFEval | 93.3% | estimated ± 3.6 pp, high confidence |
| LongBench v2 | 52.1% | estimated ± 5.5 pp, medium confidence |
| VITA-Bench | 6.8% | estimated ± 6.7 pp, low confidence |
| τ²-bench results | 44.1% | estimated ± 11.8 pp, low confidence |
| AA Coding Index | 26.8% | measured |
| APEX-Agents | 4.5% | estimated ± 9.4 pp, low confidence |
| APEX-Agents-AA | 7.0% | estimated ± 4.4 pp, medium confidence |
| BioMysteryBench (human-difficult) | 0.0% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 61.7% | estimated ± 4.5 pp, medium confidence |
| SWE-bench Verified | 52.8% | measured |
| AutomationBench | 30.1% | estimated ± 9.1 pp, low confidence |
| BFCL v4 | 65.1% | estimated ± 2.7 pp, high confidence |
| CyberGym | 50.3% | estimated ± 5.3 pp, low confidence |
| JobBench | 0.0% | estimated ± 8.7 pp, low confidence |
| SWE-bench Pro | 28.4% | estimated ± 4.5 pp, high confidence |
| τ³-bench results | 9.5% | measured |
| WideResearch | 49.4% | estimated ± 3.5 pp, medium confidence |
| AA Agentic Index | 6.1% | measured |
| MMLU-Pro | 81.6% | measured |
| AA-IFBench | 58.1% | estimated ± 7.4 pp, medium confidence |
| BBH | 96.9% | estimated ± 2.8 pp, medium confidence |
| GPQA | 75.6% | measured |
| MMLU | 80.3% | estimated ± 0.9 pp, high confidence |
| Vals GPQA Diamond | 75.7% | estimated ± 2.1 pp, medium confidence |
| Vals LiveCodeBench | 81.8% | estimated ± 0.8 pp, low confidence |
| Vals MMLU-Pro | 78.2% | estimated ± 1.6 pp, medium confidence |
| MMMLU | 83.3% | estimated ± 0.7 pp, medium confidence |
| AA MMLU-Pro | 83.3% | estimated ± 0.8 pp, medium confidence |
| Gert Labs | 27.3% | estimated ± 10.0 pp, low confidence |
| AA Harvey LAB v1.0 | 79.4% | estimated ± 1.2 pp, low confidence |
| AA Tau3 Banking | 19.5% | estimated ± 3.7 pp, medium confidence |
| ARC-AGI-1 | 14.0% | estimated ± 3.9 pp, medium confidence |
| ARC-AGI-2 | 0.0% | estimated ± 10.9 pp, low confidence |
| FrontierSWE v2 | 1.5% | estimated ± 14.2 pp, low confidence |
| MazeBench | 0.4% | estimated ± 5.5 pp, low confidence |
| OSWorld-Verified | 49.6% | estimated ± 5.7 pp, low confidence |
| Vals SWE-bench | 38.4% | estimated ± 5.3 pp, low confidence |
| Terminal-Bench 2.1 (Vals AI) | 24.8% | estimated ± 7.3 pp, low confidence |
| CWE-Bench-AA | 27.0% | estimated ± 6.4 pp, low confidence |
| AA Cyber Index | 4.5% | estimated ± 9.2 pp, low confidence |
| DeepsecBench-AA | 0.0% | estimated ± 8.9 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 4.3% | estimated ± 2.5 pp, low confidence |
| AA ITBench | 34.8% | estimated ± 4.0 pp, medium confidence |
| Bug Hunt Bench | 10.2% | estimated ± 10.5 pp, low confidence |
| CWE-bench v1 | 11.5% | estimated ± 6.4 pp, low confidence |
| DeepSWE | 12.0% | estimated ± 7.5 pp, low confidence |
| DRACO | 42.1% | estimated ± 2.0 pp, low confidence |
| HLE w/o tools | 10.5% | measured |
| SWE Multilingual | 36.5% | measured |
| Toolathlon-Verified | 20.8% | estimated ± 2.3 pp, low confidence |
| VulcanBench Frontier v4 | 60.1% | estimated ± 6.8 pp, low confidence |
| GDP.pdf | 17.0% | estimated ± 4.6 pp, medium confidence |
| ARC-AGI-3 | 0.0% | estimated ± 7.2 pp, low confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| Vibe Code Bench | 0.0% | estimated ± 8.4 pp, low confidence |
| Hermes Bench | 26.9% | estimated ± 2.9 pp, medium confidence |
| Hermes Index | 6.9% | estimated ± 8.7 pp, low confidence |
| ExploitGym | 0.0% | estimated ± 10.6 pp, low confidence |
| C-Eval | 87.2% | estimated ± 1.0 pp, low confidence |
| Claw-Eval | 62.7% | estimated ± 6.4 pp, low confidence |
| MCP Atlas | 64.6% | estimated ± 7.8 pp, low confidence |
| MMLU-Redux | 91.3% | estimated ± 0.6 pp, high confidence |
| NL2Repo | 17.0% | estimated ± 4.7 pp, medium confidence |
| QwenClawBench | 55.9% | estimated ± 6.0 pp, low confidence |
| SuperGPQA | 55.6% | estimated ± 8.5 pp, low confidence |
| Toolathlon | 16.7% | estimated ± 4.2 pp, medium confidence |
| AA LiveCodeBench | 84.0% | estimated ± 4.7 pp, low confidence |
| HealthBench Hard | 0.0% | estimated ± 8.6 pp, low confidence |
| MMLU-Pro (Arcee) | 81.4% | estimated ± 3.4 pp, medium confidence |
| React Native Evals | 67.4% | estimated ± 2.7 pp, low confidence |
| ResearchClawBench | 8.9% | estimated ± 1.9 pp, medium confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (length-adjusted) | 54.1% | estimated ± 3.7 pp, medium confidence |
| HealthBench Professional | 56.7% | estimated ± 4.2 pp, low confidence |
| ScarfBench | 24.4% | estimated ± 9.1 pp, low confidence |
| STEMBench | 2.3% | estimated ± 0.2 pp, low confidence |
| SimpleQA | 10.8% | estimated ± 4.3 pp, low confidence |
| LiveCodeBench | 60.5% | estimated ± 14.6 pp, low confidence |
| OpenHarmony Bench v1.0 | 51.0% | estimated ± 2.4 pp, medium confidence |
| MRCRv2 | 22.9% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 59.3% | estimated ± 2.6 pp, low confidence |
| BioBasicsBench | 7.2% | estimated ± 10.2 pp, low confidence |
| PinchBench | 83.4% | measured |