CESBench - Countermeasures: leaderboard

Metric: Composite score (%; mean over the four task types of the item-score means within the D4 countermeasures sub-domain (62 items); 380 expert-written items on cryptographic engineering security for IoT devices; zero-shot, temperature 0, no tools, provider default reasoning mode; judgment and scenario answers scored by a Qwen3.5-397B judge from outside the evaluated set). Source: arxiv.org. Saturation forecast: Around December 2026. 11 models tracked.

Top models

#ModelScore
1Kimi K2.685.5
2GLM-5.285.3
3Gemini 3.7 Flash83.3
4GPT-5.6 Luna81.6
5DeepSeek V4 Pro79.5
6DeepSeek V373.2
7MiniMax-M2.567.4
8GLM-4 32B (0414)57.9
9Llama 4 Maverick56.9
10Ling-flash-2.053.8
11Hunyuan A13B-Instruct52.5

Interactive version: theaggregate.ai/benchmark?slug=cesbench-countermeasures · How It Works · Data refreshed daily, snapshot 2026-09-26.