Recent studyBlind TTS Elo is live. Compare two anonymous voice samples, vote after listening, and help separate real preference signal from noise.Vote in the study ->
Codesota · Models · NVIDIA-Nemotron-3-Nano-30B-A3B-BF165 results · 5 benchmarks
Model card

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16.

unknown
§ 02 · Benchmarks

Every benchmark NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01AIME 2025Reasoning · Mathematical Reasoningaccuracy89.1%#10/22source ↗
02LiveCodeBenchComputer Code · Code Generationpass-168.3%#18/24source ↗
03HLEReasoning · Multi-step Reasoningaccuracy10.6%#31/36source ↗
04GPQA DiamondReasoning · Multi-step Reasoningaccuracy73.0%#45/74source ↗
05MMLU-ProReasoning · Commonsense Reasoningaccuracy78.3%#47/73source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 actually performs.

Computer Code
1
benchmark
avg rank #18.0
Reasoning
4
benchmarks
avg rank #33.3
§ 04 · Papers

1 paper with results for NVIDIA-Nemotron-3-Nano-30B-A3B-BF16.

  1. 2025-12-23· 5 results

    Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
5
results
0 of 5 rows marked verified.