NVIDIA
availableShows if the model has enough results for an index.Nemotron 3 Nano Omni 30B A3B
Nemotron 3 Nano Omni 30B A3B is a reasoning model from NVIDIA in the Nemotron 3 Nano Omni family. 19 benchmarks count toward its score, in 7 categories.
IndexOverall score out of 100.36.9 ±4.2
CoverageShare of the index weight with results.95%
SpeedOutput tokens per second.269/s
Input / 1MUS dollars per 1M input tokens.Free
Output / 1MUS dollars per 1M output tokens.Free
ContextMaximum tokens in one request.256K
EloLMArena rating and rank.N/A
The index is a score out of 100. The ± range shows how much it can change.
CapabilitiesScore per category, out of 100.
Out of 100Results
19 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result as a score out of 100. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| RefCOCO average | Multimodal | 90.5% | — | — | — | RefCOCO dataset authors |
| AI2D test split | Multimodal | 88.5% | — | — | — | Qwen |
| American Invitational Mathematics Examination 2025 | Math | 82.1% | 41.7 | — | — | Mathematical Association of America |
| Massive Multitask Language Understanding Professional | Knowledge | 77.3% | 42.3 | — | — | Yubo Wang et al. |
| CharXiv Reasoning | Multimodal | 76.3% | 52.9 | — | — | CharXiv authors |
| Instruction Following Benchmark | Instruction | 74.2% | 52.4 | — | — | Benchmark authors |
| Video-MME without subtitle | Multimodal | 72.2% | — | — | — | Qwen |
| Graduate-Level Google-Proof Q&A | Knowledge | 72.2% | 44.9 | — | — | David Rein et al. |
| GPQA Diamond | Knowledge | 72.2% | 44.9 | — | — | David Rein et al. |
| Massive Multi-discipline Multimodal Understanding | Multimodal | 70.8% | 40.3 | — | — | MMMU authors |
| LiveCodeBench v5 | Coding | 63.2% | — | — | — | LiveCodeBench maintainers |
| Artificial Analysis IFBench | Instruction | 63.2% | 53.2 | — | — | Artificial Analysis |
| ScreenSpot Pro | Multimodal | 57.8% | 38.8 | — | — | Kaixin Li et al. |
| MMLongBench-Doc | Multimodal | 57.5% | — | — | — | Qwen |
| Artificial Analysis MMMU-Pro | Multimodal | 53.2% | 32.1 | — | — | Artificial Analysis |
| OSWorld | Agentic | 47.4% | — | — | — | Z.AI |
| Artificial Analysis GPQA Diamond | Knowledge | 46.9% | 16.6 | — | — | Artificial Analysis |
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 45.3% | 31.3 | — | — | Victor Barres et al. |
| Artificial Analysis Long Context Reasoning | Reasoning | 39.7% | 35.7 | — | — | Artificial Analysis |
| Scientific Code Benchmark | Coding | 32.0% | 41.4 | — | — | Benchmark authors |
| Artificial Analysis Omniscience Accuracy | Knowledge | 15.2% | 32.7 | — | — | Artificial Analysis |
| Artificial Analysis Coding Index | Coding | 13.8% | 28.7 | — | — | Artificial Analysis |
| Artificial Analysis Intelligence Index | Knowledge | 10.3% | 35.2 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 4.8% | 29.8 | — | — | Artificial Analysis |
| GDPval-AA normalized | Agentic | 0.0% | 35.6 | — | — | Artificial Analysis |
| Critical Physics Tasks | Reasoning | 0.0% | 38.4 | — | — | Artificial Analysis |
19 benchmarks count, from 20 of 26 results. A grey row does not count. Too few models took that benchmark.