NuclearQAv2: leaderboard

Metric: Aggregated accuracy (%) over all 1,239 questions (750 boolean, 206 numeric, 283 verbal); mean of three runs; answers requested without reasoning text. Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked.

Top models

#ModelScore
1GPT-OSS-120B79.23
2GPT-5.478.91
3GPT-5.278.42
4NVIDIA-Nemotron-3-Super-120B-A12B-FP878.4
5GPT-4o72.45
6Llama 3 70B Instruct70.92
7Llama 3 8B Instruct62.36
8Nova Pro60.37
9Mistral 7B Instruct35.48

Interactive version: theaggregate.ai/benchmark?slug=nuclearqav2 · How It Works · Data refreshed daily, snapshot 2026-09-29.