# Nemotron 3.5 Super VL 120B A12B NVFP4 benchmark scores

NVIDIA · model · https://benchgap.net/model/nemotron-3-5-super-vl-120b-a12b-nvfp4 · data retrieved 2026-10-29

As of 2026-10-29, Nemotron 3.5 Super VL 120B A12B NVFP4 (NVIDIA) has measured scores on 23 benchmarks and estimated scores on 117 more.

| Benchmark | Score | Source |
|---|---|---|
| [AA-GPQA Diamond](https://benchgap.net/b/aa-gpqa-diamond/current.md) | 88.0% | estimated ± 2.7 pp, high confidence |
| [AA-HLE](https://benchgap.net/b/aa-hle/current.md) | 30.7% | measured |
| [AA-SciCode](https://benchgap.net/b/aa-sci-code/current.md) | 47.8% | measured |
| [CritPt](https://benchgap.net/b/critpt/current.md) | 10.6% | measured |
| [GDPval-AA](https://benchgap.net/b/gdpvalaanormalized/current.md) | 33.1% | measured |
| [GPQA Diamond](https://benchgap.net/b/gpqa-diamond/current.md) | 89.9% | measured |
| [HLE](https://benchgap.net/b/hle/current.md) | 29.0% | measured |
| [IFBench](https://benchgap.net/b/ifbench/current.md) | 71.5% | measured |
| [AA-LCR](https://benchgap.net/b/lcr/current.md) | 67.7% | measured |
| [LiveCodeBench v6](https://benchgap.net/b/livecodebench-v6/current.md) | 87.4% | measured |
| [SciCode](https://benchgap.net/b/scicode/current.md) | 47.7% | estimated ± 3.1 pp, high confidence |
| [Terminal-Bench 2.1](https://benchgap.net/b/terminalbench21/current.md) | 60.8% | measured |
| [BrowseComp](https://benchgap.net/b/browsecomp/current.md) | 77.5% | measured |
| [HLE w/ tools](https://benchgap.net/b/hlewithtools/current.md) | 49.8% | estimated ± 5.3 pp, medium confidence |
| [IFEval](https://benchgap.net/b/ifeval/current.md) | 93.0% | estimated ± 3.6 pp, high confidence |
| [LongBench v2](https://benchgap.net/b/longbench-v2/current.md) | 59.8% | estimated ± 5.8 pp, low confidence |
| [VITA-Bench](https://benchgap.net/b/vitabench/current.md) | 44.0% | estimated ± 6.7 pp, low confidence |
| [τ²-bench results](https://benchgap.net/b/tau2-bench/current.md) | 93.1% | estimated ± 11.5 pp, low confidence |
| [AA Coding Index](https://benchgap.net/b/aa-coding-index/current.md) | 42.0% | estimated ± 5.3 pp, medium confidence |
| [AA-MMMU-Pro](https://benchgap.net/b/aa-mmmu-pro/current.md) | 71.6% | estimated ± 2.1 pp, high confidence |
| [APEX-Agents](https://benchgap.net/b/apexagents/current.md) | 25.4% | estimated ± 9.0 pp, low confidence |
| [APEX-Agents-AA](https://benchgap.net/b/apexagentsaa/current.md) | 23.7% | estimated ± 4.2 pp, high confidence |
| [BioMysteryBench (human-difficult)](https://benchgap.net/b/biomysterybenchhumandifficult/current.md) | 44.3% | estimated ± 6.8 pp, low confidence |
| [DeepSearchQA](https://benchgap.net/b/deepsearchqa/current.md) | 83.8% | estimated ± 7.3 pp, low confidence |
| [SWE-bench Verified](https://benchgap.net/b/swe-bench-verified/current.md) | 71.1% | measured |
| [AutomationBench](https://benchgap.net/b/automationbench/current.md) | 27.2% | estimated ± 10.5 pp, low confidence |
| [BFCL v4](https://benchgap.net/b/bfcl-v4/current.md) | 74.9% | estimated ± 2.7 pp, medium confidence |
| [CyberGym](https://benchgap.net/b/cybergym/current.md) | 63.9% | estimated ± 6.0 pp, medium confidence |
| [JobBench](https://benchgap.net/b/jobbench/current.md) | 32.3% | estimated ± 8.7 pp, medium confidence |
| [SWE-bench Pro](https://benchgap.net/b/swe-bench-pro/current.md) | 51.3% | measured |
| [τ³-bench results](https://benchgap.net/b/tau3-bench/current.md) | 17.8% | measured |
| [WideResearch](https://benchgap.net/b/wideresearch/current.md) | 76.6% | estimated ± 3.5 pp, high confidence |
| [AA Agentic Index](https://benchgap.net/b/aa-agentic-index/current.md) | 26.6% | estimated ± 2.9 pp, high confidence |
| [MMLU-Pro](https://benchgap.net/b/mmlu-pro/current.md) | 85.3% | estimated ± 2.5 pp, medium confidence |
| [AA-IFBench](https://benchgap.net/b/aa-if-bench/current.md) | 56.9% | estimated ± 7.4 pp, medium confidence |
| [Artificial Analysis Intelligence Index](https://benchgap.net/b/artificialanalysis/current.md) | 13.6% | measured |
| [GPQA](https://benchgap.net/b/gpqa/current.md) | 89.8% | estimated ± 1.2 pp, high confidence |
| [MMLU](https://benchgap.net/b/mmlu/current.md) | 89.6% | estimated ± 0.7 pp, high confidence |
| [AA-Omniscience Accuracy](https://benchgap.net/b/omniscienceaccuracy/current.md) | 25.9% | measured |
| [MMMLU](https://benchgap.net/b/mmmlu/current.md) | 89.6% | estimated ± 0.7 pp, medium confidence |
| [MMMU](https://benchgap.net/b/mmmu/current.md) | 82.2% | estimated ± 3.7 pp, high confidence |
| [AA MMLU-Pro](https://benchgap.net/b/aa-mmlu-pro/current.md) | 84.6% | estimated ± 0.6 pp, high confidence |
| [Gert Labs](https://benchgap.net/b/gertlabs/current.md) | 58.7% | estimated ± 7.4 pp, medium confidence |
| [AA EnterpriseOps-Gym](https://benchgap.net/b/aa-enterprise-ops-gym/current.md) | 41.5% | estimated ± 3.3 pp, medium confidence |
| [AA Harvey LAB v1.0](https://benchgap.net/b/aa-harvey-lab/current.md) | 89.9% | estimated ± 9.8 pp, low confidence |
| [AA Tau3 Banking](https://benchgap.net/b/aa-tau3-banking/current.md) | 33.5% | estimated ± 3.9 pp, high confidence |
| [AA Terminal-Bench 2.1](https://benchgap.net/b/aa-terminal-bench21/current.md) | 67.8% | estimated ± 6.8 pp, low confidence |
| [ARC-AGI-1](https://benchgap.net/b/arcagi1/current.md) | 88.9% | estimated ± 2.7 pp, high confidence |
| [ARC-AGI-2](https://benchgap.net/b/arc-agi-2/current.md) | 55.3% | estimated ± 10.1 pp, low confidence |
| [CursorBench 3.1](https://benchgap.net/b/cursor-bench31/current.md) | 38.6% | estimated ± 3.4 pp, low confidence |
| [CursorBench 3.2](https://benchgap.net/b/cursor-bench32/current.md) | 43.1% | estimated ± 3.6 pp, medium confidence |
| [Terminal-Bench 3.0](https://benchgap.net/b/terminal-bench-3/current.md) | 5.5% | estimated ± 9.1 pp, low confidence |
| [FrontierCode 1.1 Main](https://benchgap.net/b/frontiercode/current.md) | 4.6% | estimated ± 2.7 pp, low confidence |
| [FrontierSWE v2](https://benchgap.net/b/frontierswev2/current.md) | 0.0% | estimated ± 9.0 pp, low confidence |
| [MazeBench](https://benchgap.net/b/mazebench/current.md) | 0.4% | estimated ± 5.4 pp, low confidence |
| [OSWorld-Verified](https://benchgap.net/b/osworld-verified/current.md) | 70.1% | estimated ± 5.8 pp, medium confidence |
| [ParseBench](https://benchgap.net/b/parsebench/current.md) | 57.4% | estimated ± 8.0 pp, low confidence |
| [Vals GPQA Diamond](https://benchgap.net/b/vals-gpqa-diamond/current.md) | 89.1% | estimated ± 2.0 pp, high confidence |
| [Vals LiveCodeBench](https://benchgap.net/b/valslivecodebench/current.md) | 84.7% | estimated ± 2.0 pp, low confidence |
| [Vals MMLU-Pro](https://benchgap.net/b/vals-mmlu-pro/current.md) | 86.6% | estimated ± 1.6 pp, high confidence |
| [Vals SWE-bench](https://benchgap.net/b/valsswebench/current.md) | 64.1% | estimated ± 6.8 pp, medium confidence |
| [Terminal-Bench 2.1 (Vals AI)](https://benchgap.net/b/vals-terminal-bench21/current.md) | 52.9% | estimated ± 7.4 pp, medium confidence |
| [AA AutomationBench](https://benchgap.net/b/aa-automation-bench/current.md) | 33.4% | estimated ± 14.8 pp, low confidence |
| [CWE-Bench-AA](https://benchgap.net/b/aa-cwe-bench/current.md) | 43.8% | estimated ± 5.8 pp, medium confidence |
| [AA Cyber Index](https://benchgap.net/b/aa-cyber-index/current.md) | 37.4% | estimated ± 13.3 pp, low confidence |
| [DeepsecBench-AA](https://benchgap.net/b/aa-deepsec-bench/current.md) | 4.9% | estimated ± 8.6 pp, medium confidence |
| [GDP.pdf](https://benchgap.net/b/aa-gdp-pdf/current.md) | 10.8% | estimated ± 4.9 pp, medium confidence |
| [AA ITBench](https://benchgap.net/b/aa-itbench/current.md) | 44.6% | estimated ± 4.1 pp, high confidence |
| [AA Terminal-Bench 4.0](https://benchgap.net/b/aa-terminal-bench4/current.md) | 3.9% | estimated ± 11.6 pp, low confidence |
| [CursorBench 4.0](https://benchgap.net/b/cursor-bench40/current.md) | 23.8% | estimated ± 3.5 pp, medium confidence |
| [CWE-bench v1](https://benchgap.net/b/cwe-bench-v1/current.md) | 42.4% | estimated ± 6.4 pp, medium confidence |
| [DeepSWE](https://benchgap.net/b/deepswe/current.md) | 51.9% | estimated ± 7.5 pp, low confidence |
| [FrontierCode 2.0](https://benchgap.net/b/frontiercode-2/current.md) | 18.3% | estimated ± 7.1 pp, low confidence |
| [HLE w/o tools](https://benchgap.net/b/hlenotools/current.md) | 31.4% | measured |
| [OSWorld 2.1](https://benchgap.net/b/osworld-2-1/current.md) | 49.0% | estimated ± 6.0 pp, low confidence |
| [PostTrainBench v1.1](https://benchgap.net/b/posttrainbench-v1-1/current.md) | 20.6% | estimated ± 4.7 pp, medium confidence |
| [SWE Multilingual](https://benchgap.net/b/swe-bench-multilingual/current.md) | 67.0% | measured |
| [Toolathlon-Verified](https://benchgap.net/b/toolathlonverified/current.md) | 59.4% | estimated ± 3.1 pp, high confidence |
| [OSWorld 2.1 Offline](https://benchgap.net/b/osworld-2-1-offline/current.md) | 32.0% | estimated ± 7.9 pp, low confidence |
| [Vibe Code Bench](https://benchgap.net/b/vibecodebench/current.md) | 0.8% | estimated ± 8.1 pp, medium confidence |
| [ARC-AGI-3](https://benchgap.net/b/arcagi3/current.md) | 0.0% | estimated ± 3.6 pp, high confidence |
| [ARC-AGI-3 Provider Adapter](https://benchgap.net/b/arc-agi-3-provider-adapter/current.md) | 2.8% | estimated ± 7.5 pp, low confidence |
| [Hermes Bench](https://benchgap.net/b/hermesbench/current.md) | 62.0% | estimated ± 2.9 pp, high confidence |
| [Hermes Index](https://benchgap.net/b/hermesindex/current.md) | 29.2% | estimated ± 8.7 pp, medium confidence |
| [CharXiv](https://benchgap.net/b/charxiv/current.md) | 79.9% | measured |
| [CharXiv w/o tools](https://benchgap.net/b/charxivnotools/current.md) | 77.5% | estimated ± 2.2 pp, medium confidence |
| [ExploitGym](https://benchgap.net/b/exploitgym/current.md) | 0.0% | estimated ± 9.2 pp, low confidence |
| [AI2D_TEST](https://benchgap.net/b/ai2dtest/current.md) | 93.4% | estimated ± 0.9 pp, medium confidence |
| [C-Eval](https://benchgap.net/b/ceval/current.md) | 92.9% | estimated ± 0.9 pp, medium confidence |
| [Claw-Eval](https://benchgap.net/b/claw-eval/current.md) | 62.7% | estimated ± 7.6 pp, low confidence |
| [CountBench](https://benchgap.net/b/countbench/current.md) | 91.7% | estimated ± 1.3 pp, medium confidence |
| [DynaMath](https://benchgap.net/b/dynamath/current.md) | 85.6% | estimated ± 0.8 pp, medium confidence |
| [ERQA](https://benchgap.net/b/erqa/current.md) | 65.0% | estimated ± 4.9 pp, high confidence |
| [INCLUDE](https://benchgap.net/b/include/current.md) | 82.8% | estimated ± 2.0 pp, low confidence |
| [MathVision](https://benchgap.net/b/mathvision/current.md) | 77.8% | measured |
| [MCP Atlas](https://benchgap.net/b/mcpatlas/current.md) | 73.2% | estimated ± 10.7 pp, low confidence |
| [MLVU (M-Avg)](https://benchgap.net/b/mlvuavg/current.md) | 82.3% | estimated ± 1.5 pp, high confidence |
| [MMLU-ProX](https://benchgap.net/b/mmluprox/current.md) | 82.7% | estimated ± 1.3 pp, medium confidence |
| [MMLU-Redux](https://benchgap.net/b/mmluredux/current.md) | 94.2% | estimated ± 0.8 pp, medium confidence |
| [MMMU-Pro](https://benchgap.net/b/mmmu-pro/current.md) | 78.0% | estimated ± 2.9 pp, high confidence |
| [NL2Repo](https://benchgap.net/b/nl2repo/current.md) | 33.5% | estimated ± 2.8 pp, high confidence |
| [OmniDocBench 1.5](https://benchgap.net/b/omnidocbench15/current.md) | 87.1% | estimated ± 2.2 pp, high confidence |
| [QwenClawBench](https://benchgap.net/b/qwenclawbench/current.md) | 87.1% | estimated ± 6.0 pp, low confidence |
| [RealWorldQA](https://benchgap.net/b/realworldqa/current.md) | 83.4% | estimated ± 1.5 pp, high confidence |
| [ScreenSpot Pro](https://benchgap.net/b/screenspot-pro/current.md) | 71.6% | estimated ± 7.1 pp, medium confidence |
| [SimpleVQA](https://benchgap.net/b/simplevqa/current.md) | 62.2% | estimated ± 7.3 pp, medium confidence |
| [SuperGPQA](https://benchgap.net/b/supergpqa/current.md) | 69.9% | estimated ± 6.9 pp, medium confidence |
| [Toolathlon](https://benchgap.net/b/toolathlon/current.md) | 47.0% | estimated ± 4.2 pp, high confidence |
| [V*](https://benchgap.net/b/vstar/current.md) | 86.0% | measured |
| [Video-MME (w/o subtitle)](https://benchgap.net/b/videommenosub/current.md) | 81.2% | estimated ± 4.9 pp, medium confidence |
| [Video-MME (with subtitle)](https://benchgap.net/b/videommewithsub/current.md) | 82.2% | estimated ± 1.9 pp, high confidence |
| [VideoMMMU](https://benchgap.net/b/videommmu/current.md) | 85.3% | estimated ± 1.5 pp, medium confidence |
| [We-Math](https://benchgap.net/b/wemath/current.md) | 69.3% | estimated ± 2.1 pp, medium confidence |
| [HealthBench Hard](https://benchgap.net/b/healthbench-hard/current.md) | 29.3% | estimated ± 8.6 pp, low confidence |
| [LiveCodeBench Pro](https://benchgap.net/b/livecodebench-pro/current.md) | 76.5% | estimated ± 6.0 pp, low confidence |
| [MedXpertQA (MM)](https://benchgap.net/b/medxpertqamm/current.md) | 75.0% | estimated ± 6.4 pp, low confidence |
| [MedXpertQA (Text)](https://benchgap.net/b/medxpertqatext/current.md) | 53.5% | estimated ± 4.5 pp, medium confidence |
| [MMLU-Pro (Arcee)](https://benchgap.net/b/mmlu-pro-arcee/current.md) | 86.8% | estimated ± 3.4 pp, low confidence |
| [React Native Evals](https://benchgap.net/b/reactnativeevals/current.md) | 72.0% | estimated ± 2.3 pp, medium confidence |
| [ResearchClawBench](https://benchgap.net/b/researchclawbench/current.md) | 17.7% | estimated ± 2.2 pp, medium confidence |
| [SWE-Rebench](https://benchgap.net/b/swe-rebench/current.md) | 57.0% | estimated ± 3.6 pp, medium confidence |
| [BioMysteryBench (human-solvable)](https://benchgap.net/b/biomysterybenchhumansolvable/current.md) | 83.8% | estimated ± 0.6 pp, low confidence |
| [DRACO](https://benchgap.net/b/draco/current.md) | 75.1% | estimated ± 3.1 pp, medium confidence |
| [FrontierCode 1.1 Extended](https://benchgap.net/b/frontiercode11extended/current.md) | 52.8% | estimated ± 3.0 pp, low confidence |
| [HealthBench (raw)](https://benchgap.net/b/healthbench/current.md) | 39.6% | estimated ± 6.0 pp, low confidence |
| [HealthBench (length-adjusted)](https://benchgap.net/b/healthbenchlengthadjusted/current.md) | 53.9% | estimated ± 3.3 pp, medium confidence |
| [HealthBench Professional](https://benchgap.net/b/healthbenchprofessional/current.md) | 58.1% | estimated ± 4.5 pp, low confidence |
| [HealthBench Professional (raw)](https://benchgap.net/b/healthbenchprofessionalraw/current.md) | 50.8% | estimated ± 4.5 pp, medium confidence |
| [HLE-Verified](https://benchgap.net/b/hleverified/current.md) | 0.0% | estimated ± 6.8 pp, low confidence |
| [LABBench2](https://benchgap.net/b/labbench2/current.md) | 75.8% | estimated ± 2.4 pp, low confidence |
| [STEMBench](https://benchgap.net/b/stembench/current.md) | 2.4% | estimated ± 0.2 pp, high confidence |
| [SimpleQA](https://benchgap.net/b/simpleqa/current.md) | 26.2% | estimated ± 4.3 pp, medium confidence |
| [LiveCodeBench](https://benchgap.net/b/livecodebench/current.md) | 73.7% | estimated ± 14.6 pp, low confidence |
| [Agents' Last Exam](https://benchgap.net/b/agentslastexam/current.md) | 25.0% | estimated ± 13.0 pp, low confidence |
| [OpenHarmony Bench](https://benchgap.net/b/openharmonybench/current.md) | 51.1% | estimated ± 2.4 pp, high confidence |
| [BabyVision](https://benchgap.net/b/babyvision/current.md) | 29.5% | measured |
| [MMVU](https://benchgap.net/b/mmvu/current.md) | 70.8% | estimated ± 3.3 pp, medium confidence |
| [MRCRv2](https://benchgap.net/b/mrcrv2/current.md) | 62.4% | estimated ± 11.3 pp, low confidence |
| [MMLongBench-Doc](https://benchgap.net/b/mmlongbenchdoc/current.md) | 62.8% | measured |
| [PinchBench](https://benchgap.net/b/pinchbench/current.md) | 90.1% | estimated ± 3.6 pp, medium confidence |