CyberCertBench - Fortinet NSE: leaderboard

CyberCertBench (2026) certification knowledge test of 141 Fortinet NSE certification questions (procedural, vendor-specific configuration of the Fortinet security ecosystem), asked as 5-shot multiple choice at temperature 0. Exact accuracy (%): a question counts only when all correct options and no wrong one are chosen; higher is better.

Metric: Accuracy (%) on 141 Fortinet NSE certification questions (procedural, vendor-specific configuration of the Fortinet security ecosystem): 5-shot multiple-choice question answering at temperature 0, scored by exact accuracy (correct only when the model selects all correct options and no incorrect one), mean accuracy (%) as printed in the appendix; questions scraped from public certification question banks and checked against authoritative documentation; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 45 models tracked. Updated 3 Nov 2026.

Top models

#ModelScoreOverall rank
1Claude Sonnet 4.562.4#261
2DeepSeek V3 (0324)62.4#715
3Gemini 2.5 Pro (Preview 05-06)61.7#271
4Kimi K261#443
5Claude 3.5 Sonnet59.6#752
6GPT-4o58.2#751
7GPT-4.158.2#505
8Gemini 2.0 Flash56.7#723
9Claude Haiku 4.556#583
10Llama 4 Maverick56#1110
11GPT-5 Mini55.3#364
12Mixtral 8x22B Instruct55.3#2086
13Mistral Medium 3.155.3#863
14GPT-OSS-20B53.9#1183
15Qwen 2.5 72B53.9#1188

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=cybercertbench-fortinet-nse · How It Works · Data refreshed daily, snapshot 2026-11-21.