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
| # | Model | Score |
|---|---|---|
| 1 | GPT-OSS-120B | 79.23 |
| 2 | GPT-5.4 | 78.91 |
| 3 | GPT-5.2 | 78.42 |
| 4 | NVIDIA-Nemotron-3-Super-120B-A12B-FP8 | 78.4 |
| 5 | GPT-4o | 72.45 |
| 6 | Llama 3 70B Instruct | 70.92 |
| 7 | Llama 3 8B Instruct | 62.36 |
| 8 | Nova Pro | 60.37 |
| 9 | Mistral 7B Instruct | 35.48 |
Interactive version: theaggregate.ai/benchmark?slug=nuclearqav2 · How It Works · Data refreshed daily, snapshot 2026-09-29.