NVIDIA · model
Nemotron 3.5 Bolt 74B-A9B BF16 benchmark scores
As of 2026-10-29, Nemotron 3.5 Bolt 74B-A9B BF16 (NVIDIA) has measured scores on 9 benchmarks and estimated scores on 63 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 87.2% | estimated ± 2.7 pp, high confidence |
| AA-HLE | 32.2% | estimated ± 3.8 pp, high confidence |
| CritPt | 9.0% | estimated ± 4.6 pp, high confidence |
| GDPval-AA | 28.2% | estimated ± 7.7 pp, medium confidence |
| GPQA Diamond | 88.8% | measured |
| HLE | 34.4% | estimated ± 6.6 pp, medium confidence |
| AA-LCR | 67.4% | measured |
| Terminal-Bench 2.1 | 53.9% | measured |
| BrowseComp | 70.0% | measured |
| HLE w/ tools | 48.4% | estimated ± 5.8 pp, medium confidence |
| LongBench v2 | 59.8% | estimated ± 5.8 pp, low confidence |
| VITA-Bench | 40.2% | estimated ± 6.7 pp, low confidence |
| τ²-bench results | 92.1% | estimated ± 11.5 pp, low confidence |
| APEX-Agents | 14.3% | estimated ± 0.6 pp, low confidence |
| APEX-Agents-AA | 16.7% | estimated ± 4.2 pp, high confidence |
| DeepSearchQA | 79.9% | estimated ± 7.3 pp, low confidence |
| AutomationBench | 22.2% | estimated ± 10.5 pp, low confidence |
| BFCL v4 | 66.9% | estimated ± 2.9 pp, medium confidence |
| CyberGym | 57.9% | estimated ± 7.3 pp, medium confidence |
| JobBench | 29.2% | estimated ± 6.4 pp, medium confidence |
| τ³-bench results | 17.0% | measured |
| WideResearch | 72.7% | estimated ± 3.5 pp, high confidence |
| AA Agentic Index | 4.9% | estimated ± 5.9 pp, medium confidence |
| MMLU-Pro | 85.1% | estimated ± 2.5 pp, medium confidence |
| Artificial Analysis Intelligence Index | 17.0% | estimated ± 6.1 pp, medium confidence |
| GPQA | 88.7% | estimated ± 1.2 pp, high confidence |
| MMLU | 87.3% | estimated ± 1.0 pp, high confidence |
| AA-Omniscience Accuracy | 21.8% | measured |
| MMMLU | 89.4% | estimated ± 1.1 pp, medium confidence |
| AA MMLU-Pro | 84.3% | estimated ± 0.7 pp, medium confidence |
| Gert Labs | 49.9% | estimated ± 7.4 pp, medium confidence |
| AA EnterpriseOps-Gym | 36.4% | estimated ± 3.3 pp, low confidence |
| AA Harvey LAB v1.0 | 88.0% | estimated ± 9.8 pp, low confidence |
| AA Tau3 Banking | 28.5% | estimated ± 3.9 pp, medium confidence |
| AA Terminal-Bench 2.1 | 62.6% | estimated ± 6.8 pp, low confidence |
| ARC-AGI-1 | 87.2% | estimated ± 2.7 pp, high confidence |
| ARC-AGI-2 | 51.2% | estimated ± 10.1 pp, low confidence |
| Terminal-Bench 3.0 | 4.2% | estimated ± 9.1 pp, low confidence |
| MazeBench | 0.0% | estimated ± 6.1 pp, low confidence |
| OSWorld-Verified | 62.9% | estimated ± 5.8 pp, medium confidence |
| Vals GPQA Diamond | 88.0% | estimated ± 2.0 pp, high confidence |
| Vals MMLU-Pro | 86.0% | estimated ± 1.6 pp, high confidence |
| Terminal-Bench 2.1 (Vals AI) | 47.6% | estimated ± 7.4 pp, low confidence |
| CWE-Bench-AA | 37.3% | estimated ± 5.8 pp, medium confidence |
| AA Cyber Index | 34.4% | estimated ± 13.3 pp, low confidence |
| DeepsecBench-AA | 4.0% | estimated ± 9.1 pp, medium confidence |
| GDP.pdf | 7.5% | estimated ± 4.9 pp, low confidence |
| AA ITBench | 41.2% | estimated ± 4.1 pp, high confidence |
| AA Terminal-Bench 4.0 | 1.9% | estimated ± 11.6 pp, low confidence |
| HLE w/o tools | 28.7% | measured |
| Toolathlon-Verified | 54.6% | estimated ± 7.7 pp, medium confidence |
| ARC-AGI-3 | 0.0% | estimated ± 3.6 pp, high confidence |
| Claw-Eval | 64.3% | estimated ± 6.3 pp, low confidence |
| DeepPlanning | 37.7% | estimated ± 13.1 pp, low confidence |
| MCP Atlas | 55.6% | measured |
| MCP-Tasks | 76.0% | estimated ± 0.6 pp, low confidence |
| MMLU-Redux | 93.7% | estimated ± 0.8 pp, medium confidence |
| QwenClawBench | 54.8% | estimated ± 2.6 pp, high confidence |
| SuperGPQA | 65.0% | estimated ± 9.3 pp, medium confidence |
| Toolathlon | 40.0% | estimated ± 4.2 pp, high confidence |
| MedXpertQA (Text) | 50.5% | estimated ± 4.5 pp, medium confidence |
| MMLU-Pro (Arcee) | 86.5% | estimated ± 3.4 pp, medium confidence |
| ResearchClawBench | 16.8% | estimated ± 1.8 pp, medium confidence |
| DRACO | 64.0% | estimated ± 4.5 pp, low confidence |
| HealthBench Professional | 47.9% | estimated ± 4.8 pp, low confidence |
| HLE-Verified | 17.0% | estimated ± 7.1 pp, low confidence |
| STEMBench | 2.4% | estimated ± 0.2 pp, low confidence |
| SimpleQA | 20.6% | estimated ± 4.3 pp, medium confidence |
| Agents' Last Exam | 18.1% | estimated ± 13.0 pp, low confidence |
| MRCRv2 | 60.4% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 60.8% | estimated ± 2.6 pp, low confidence |
| PinchBench | 90.4% | measured |